Search

Multimodal learning seeks to combine data from multiple input sources to enhance the performance of different downstream tasks. In real-world scenarios, performance can degrade substantially if some input modalities are missing. Existing methods that can handle missing modalities involve custom training or adaptation steps for each input modality combination. These approaches are either tied to specific modalities or become computationally expensive as the number of input modalities increases. In this paper, we propose Masked Modality Projection (MMP), a method designed to train a single model that is robust to any missing modality scenario. We achieve this by randomly masking a subset of modalities during training and learning to project available input modalities to estimate the tokens for the masked modalities. This approach enables the model to effectively learn to leverage the information from the available modalities to compensate for the missing ones, enhancing missing modality robustness. We conduct a series of experiments with various baseline models and datasets to assess the effectiveness of this strategy. Experiments demonstrate that our approach improves robustness to different missing modality scenarios, outperforming existing methods designed for missing modalities or specific modality combinations.

Diffusion models can generate a variety of high-quality images by modeling complex data distributions. Trained diffusion models can also be very effective image priors for solving inverse problems. Most of the existing diffusion-based methods integrate data consistency steps within the diffusion reverse sampling process. The data consistency steps rely on an approximate likelihood function. In this paper, we show that the existing approximations are either insufficient or computationally inefficient. To address these issues, we propose a unified likelihood approximation method that incorporates a covariance correction term to enhance the performance and avoids propagating gradients through the diffusion model. The correction term, when integrated into the reverse diffusion sampling process, achieves better convergence towards the true data posterior for selected distributions and improves performance on real-world natural image datasets. Furthermore, we present an efficient way to factorize and invert the covariance matrix of the likelihood function for several inverse problems. We present comprehensive experiments to demonstrate the effectiveness of our method over several existing approaches.

Unauthorized privacy-related and copyrighted content generation using generative-AI is becoming a significant concern for human society, raising ethical, legal, and privacy issues that demand urgent attention. The EU's General Data Protection Regulation (GDPR) include a "right to be forgotten," which allows individuals to request the deletion of their personal data. However, this primarily applies to data stored in traditional databases, not AI models. Recently, machine unlearning techniques have arise that attempt to eliminate the influence of sensitive content used during AI model training, but they often require extensive updates to the deployed systems and incur substantial computational costs. In this work, we propose a novel and efficient method called Single Layer Unlearning Gradient (SLUG), that can unlearn targeted information by updating targeted layers of a model using a one-time gradient computation. Our method is highly modular and enables the selective removal of multiple sensitive concepts, such as celebrity names and copyrighted content, from the generated outputs of widely used foundation models (e.g., CLIP) and generative models (e.g., Stable Diffusion). Broadly, our method ensures AI-generated content complies with privacy regulations and intellectual property laws, fostering responsible use of generative models, mitigating legal risks and promoting a trustworthy, socially responsible AI ecosystem.

We introduce transformation-dependent adversarial attacks, a new class of threats where a single additive perturbation can trigger diverse, controllable mis-predictions by systematically transforming the input (e.g., scaling, blurring, compression). Unlike traditional attacks with static effects, our perturbations embed metamorphic properties to enable different adversarial attacks as a function of the transformation parameters. We demonstrate the transformation-dependent vulnerability across models (e.g., convolutional networks and vision transformers) and vision tasks (e.g., image classification and object detection). Our proposed geometric and photometric transformations enable a range of targeted errors from one crafted input (e.g., higher than 90% attack success rate for classifiers). We analyze effects of model architecture and type/variety of transformations on attack effectiveness. This work forces a paradigm shift by redefining adversarial inputs as dynamic, controllable threats. We highlight the need for robust defenses against such multifaceted, chameleon-like perturbations that current techniques are ill-prepared for.

Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing safety training techniques like Supervised Fine-tuning (SFT) and Reinforcement Learning with Human Feedback (RLHF). While further SFT and RLHF-based safety training can be conducted in multi-modal settings, collecting multi-modal training datasets poses a significant challenge. Inspired by the structural design of recent multi-modal models, where, regardless of the combination of input modalities, all inputs are ultimately fused into the language space, we aim to explore whether unlearning solely in the textual domain can be effective for cross-modality safety alignment. Our evaluation across six datasets empirically demonstrates the transferability -- textual unlearning in VLMs significantly reduces the Attack Success Rate (ASR) to less than 8\% and in some cases, even as low as nearly 2\% for both text-based and vision-text-based attacks, alongside preserving the utility. Moreover, our experiments show that unlearning with a multi-modal dataset offers no potential benefits but incurs significantly increased computational demands, possibly up to 6 times higher.

The primary focus of Neural Representation for Videos (NeRV) is to effectively model its spatiotemporal consistency. However, current NeRV systems often face a significant issue of spatial inconsistency, leading to decreased perceptual quality. To address this issue, we introduce the Pyramidal Neural Representation for Videos (PNeRV), which is built on a multi-scale information connection and comprises a lightweight rescaling operator, Kronecker Fully-connected layer (KFc), and a Benign Selective Memory (BSM) mechanism. The KFc, inspired by the tensor decomposition of the vanilla Fully-connected layer, facilitates low-cost rescaling and global correlation modeling. BSM merges high-level features with granular ones adaptively. Furthermore, we provide an analysis based on the Universal Approximation Theory of the NeRV system and validate the effectiveness of the proposed PNeRV.We conducted comprehensive experiments to demonstrate that PNeRV surpasses the performance of contemporary NeRV models, achieving the best results in video regression on UVG and DAVIS under various metrics (PSNR, SSIM, LPIPS, and FVD). Compared to vanilla NeRV, PNeRV achieves a +4.49 dB gain in PSNR and a 231% increase in FVD on UVG, along with a +3.28 dB PSNR and 634% FVD increase on DAVIS.

Plug-and-Play Priors (PnP) is a well-known class of methods for solving inverse problems in computational imaging. PnP methods combine physical forward models with learned prior models specified as image denoisers. A common issue with the learned models is that of a performance drop when there is a distribution shift between the training and testing data. Test-time training (TTT) was recently proposed as a general strategy for improving the performance of learned models when training and testing data come from different distributions. In this paper, we propose PnP-TTT as a new method for overcoming distribution shifts in PnP. PnP-TTT uses deep equilibrium learning (DEQ) for optimizing a self-supervised loss at the fixed points of PnP iterations. PnP-TTT can be directly applied on a single test sample to improve the generalization of PnP. We show through simulations that given a sufficient number of measurements, PnP-TTT enables the use of image priors trained on natural images for image reconstruction in magnetic resonance imaging (MRI).

The capability to accurately estimate 3D human poses is crucial for diverse fields such as action recognition, gait recognition, and virtual/augmented reality. However, a persistent and significant challenge within this field is the accurate prediction of human poses under conditions of severe occlusion. Traditional image-based estimators struggle with heavy occlusions due to a lack of temporal context, resulting in inconsistent predictions. While video-based models benefit from processing temporal data, they encounter limitations when faced with prolonged occlusions that extend over multiple frames. This challenge arises because these models struggle to generalize beyond their training datasets, and the variety of occlusions is hard to capture in the training data. Addressing these challenges, we propose STRIDE (Single-video based TempoRally contInuous Occlusion-Robust 3D Pose Estimation), a novel Test-Time Training (TTT) approach to fit a human motion prior for each video. This approach specifically handles occlusions that were not encountered during the model's training. By employing STRIDE, we can refine a sequence of noisy initial pose estimates into accurate, temporally coherent poses during test time, effectively overcoming the limitations of prior methods. Our framework demonstrates flexibility by being model-agnostic, allowing us to use any off-the-shelf 3D pose estimation method for improving robustness and temporal consistency. We validate STRIDE's efficacy through comprehensive experiments on challenging datasets like Occluded Human3.6M, Human3.6M, and OCMotion, where it not only outperforms existing single-image and video-based pose estimation models but also showcases superior handling of substantial occlusions, achieving fast, robust, accurate, and temporally consistent 3D pose estimates. Code is made publicly available at https://github.com/take2rohit/stride, Comment: Paper accepted at IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)-2025

Deep learning-based methods deliver state-of-the-art performance for solving inverse problems that arise in computational imaging. These methods can be broadly divided into two groups: (1) learn a network to map measurements to the signal estimate, which is known to be fragile; (2) learn a prior for the signal to use in an optimization-based recovery. Despite the impressive results from the latter approach, many of these methods also lack robustness to shifts in data distribution, measurements, and noise levels. Such domain shifts result in a performance gap and in some cases introduce undesired artifacts in the estimated signal. In this paper, we explore the qualitative and quantitative effects of various domain shifts and propose a flexible and parameter efficient framework that adapt pretrained networks to such shifts. We demonstrate the effectiveness of our method for a number of natural image, MRI, and CT reconstructions tasks under domain, measurement model, and noise-level shifts. Our experiments demonstrate that our method provides significantly better performance and parameter efficiency compared to existing domain adaptation techniques.

Multi-task and multi-domain learning methods seek to learn multiple tasks/domains, jointly or one after another, using a single unified network. The key challenge and opportunity is to exploit shared information across tasks and domains to improve the efficiency of the unified network. The efficiency can be in terms of accuracy, storage cost, computation, or sample complexity. In this paper, we propose a factorized tensor network (FTN) that can achieve accuracy comparable to independent single-task/domain networks with a small number of additional parameters. FTN uses a frozen backbone network from a source model and incrementally adds task/domain-specific low-rank tensor factors to the shared frozen network. This approach can adapt to a large number of target domains and tasks without catastrophic forgetting. Furthermore, FTN requires a significantly smaller number of task-specific parameters compared to existing methods. We performed experiments on widely used multi-domain and multi-task datasets. We show the experiments on convolutional-based architecture with different backbones and on transformer-based architecture. We observed that FTN achieves similar accuracy as single-task/domain methods while using only a fraction of additional parameters per task.

Multimodal learning seeks to utilize data from multiple sources to improve the overall performance of downstream tasks. It is desirable for redundancies in the data to make multimodal systems robust to missing or corrupted observations in some correlated modalities. However, we observe that the performance of several existing multimodal networks significantly deteriorates if one or multiple modalities are absent at test time. To enable robustness to missing modalities, we propose a simple and parameter-efficient adaptation procedure for pretrained multimodal networks. In particular, we exploit modulation of intermediate features to compensate for the missing modalities. We demonstrate that such adaptation can partially bridge performance drop due to missing modalities and outperform independent, dedicated networks trained for the available modality combinations in some cases. The proposed adaptation requires extremely small number of parameters (e.g., fewer than 1% of the total parameters) and applicable to a wide range of modality combinations and tasks. We conduct a series of experiments to highlight the missing modality robustness of our proposed method on five different multimodal tasks across seven datasets. Our proposed method demonstrates versatility across various tasks and datasets, and outperforms existing methods for robust multimodal learning with missing modalities., Comment: Accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). 28 pages, 6 figures, 17 tables

Plug-and-Play (PnP) priors is a widely-used family of methods for solving imaging inverse problems by integrating physical measurement models with image priors specified using image denoisers. PnP methods have been shown to achieve state-of-the-art performance when the prior is obtained using powerful deep denoisers. Despite extensive work on PnP, the topic of distribution mismatch between the training and testing data has often been overlooked in the PnP literature. This paper presents a set of new theoretical and numerical results on the topic of prior distribution mismatch and domain adaptation for alternating direction method of multipliers (ADMM) variant of PnP. Our theoretical result provides an explicit error bound for PnP-ADMM due to the mismatch between the desired denoiser and the one used for inference. Our analysis contributes to the work in the area by considering the mismatch under nonconvex data-fidelity terms and expansive denoisers. Our first set of numerical results quantifies the impact of the prior distribution mismatch on the performance of PnP-ADMM on the problem of image super-resolution. Our second set of numerical results considers a simple and effective domain adaption strategy that closes the performance gap due to the use of mismatched denoisers. Our results suggest the relative robustness of PnP-ADMM to prior distribution mismatch, while also showing that the performance gap can be significantly reduced with few training samples from the desired distribution.

Leveraging information across diverse modalities is known to enhance performance on multimodal segmentation tasks. However, effectively fusing information from different modalities remains challenging due to the unique characteristics of each modality. In this paper, we propose a novel fusion strategy that can effectively fuse information from different modality combinations. We also propose a new model named Multi-Modal Segmentation TransFormer (MMSFormer) that incorporates the proposed fusion strategy to perform multimodal material and semantic segmentation tasks. MMSFormer outperforms current state-of-the-art models on three different datasets. As we begin with only one input modality, performance improves progressively as additional modalities are incorporated, showcasing the effectiveness of the fusion block in combining useful information from diverse input modalities. Ablation studies show that different modules in the fusion block are crucial for overall model performance. Furthermore, our ablation studies also highlight the capacity of different input modalities to improve performance in the identification of different types of materials. The code and pretrained models will be made available at https://github.com/csiplab/MMSFormer., Comment: Accepted by IEEE Open Journal of Signal Processing. 15 pages, 3 figures, 9 tables

Existing implicit neural representation (INR) methods do not fully exploit spatiotemporal redundancies in videos. Index-based INRs ignore the content-specific spatial features and hybrid INRs ignore the contextual dependency on adjacent frames, leading to poor modeling capability for scenes with large motion or dynamics. We analyze this limitation from the perspective of function fitting and reveal the importance of frame difference. To use explicit motion information, we propose Difference Neural Representation for Videos (DNeRV), which consists of two streams for content and frame difference. We also introduce a collaborative content unit for effective feature fusion. We test DNeRV for video compression, inpainting, and interpolation. DNeRV achieves competitive results against the state-of-the-art neural compression approaches and outperforms existing implicit methods on downstream inpainting and interpolation for $960 \times 1920$ videos.

Digital radiography (DR) is becoming popular for the point of care imaging in the recent past. To reduce the radiation exposure, controlled radiation based on as low as reasonably achievable (ALARA) principle is employed and this results in low contrast images. To address this issue, post-processing algorithms such as the Multiscale Image Contrast Amplification (MUSICA) algorithm can be used to enhance the contrast of DR images even with a low radiation dose. In this study, a modification of the MUSICA algorithm is investigated to determine the potential for further contrast improvement specifically for DR images. The conclusion is that combining log compression and its inverse at the appropriate stage with a multi-stage MUSICA and denoising is very promising. The proposed method resulted in an average of 66.5 % increase in the mean contrast-to-noise ratio (CNR) for the test images considered., Comment: 4 pages, 4 figures

Conventional ultrasound (US) imaging employs the delay and sum (DAS) receive beamforming with dynamic receive focus for image reconstruction due to its simplicity and robustness. However, the DAS beamforming follows a geometrical method of delay estimation with a spatially constant speed-of-sound (SoS) of 1540 m/s throughout the medium irrespective of the tissue in-homogeneity. This approximation leads to errors in delay estimations that accumulate with depth and degrades the resolution, contrast and overall accuracy of the US image. In this work, we propose a fast marching based DAS for focused transmissions which leverages the approximate SoS map to estimate the refraction corrected propagation delays for each pixel in the medium. The proposed approach is validated qualitatively and quantitatively for imaging depths of upto ~ 11 cm through simulations, where fat layer induced aberration is employed to alter the SoS in the medium. To the best of authors' knowledge, this is the first work considering the effect of SoS on image quality for deeper imaging., Comment: 5 pages, 4 figures

We propose an approach for adversarial attacks on dense prediction models (such as object detectors and segmentation). It is well known that the attacks generated by a single surrogate model do not transfer to arbitrary (blackbox) victim models. Furthermore, targeted attacks are often more challenging than the untargeted attacks. In this paper, we show that a carefully designed ensemble can create effective attacks for a number of victim models. In particular, we show that normalization of the weights for individual models plays a critical role in the success of the attacks. We then demonstrate that by adjusting the weights of the ensemble according to the victim model can further improve the performance of the attacks. We performed a number of experiments for object detectors and segmentation to highlight the significance of the our proposed methods. Our proposed ensemble-based method outperforms existing blackbox attack methods for object detection and segmentation. Finally we show that our proposed method can also generate a single perturbation that can fool multiple blackbox detection and segmentation models simultaneously. Code is available at https://github.com/CSIPlab/EBAD., Comment: CVPR 2023 Accepted

With the rise of cameras and smart sensors, humanity generates an exponential amount of data. This valuable information, including underrepresented cases like AI in medical settings, can fuel new deep-learning tools. However, data scientists must prioritize ensuring privacy for individuals in these untapped datasets, especially for images or videos with faces, which are prime targets for identification methods. Proposed solutions to de-identify such images often compromise non-identifying facial attributes relevant to downstream tasks. In this paper, we introduce Disguise, a novel algorithm that seamlessly de-identifies facial images while ensuring the usability of the modified data. Unlike previous approaches, our solution is firmly grounded in the domains of differential privacy and ensemble-learning research. Our method involves extracting and substituting depicted identities with synthetic ones, generated using variational mechanisms to maximize obfuscation and non-invertibility. Additionally, we leverage supervision from a mixture-of-experts to disentangle and preserve other utility attributes. We extensively evaluate our method using multiple datasets, demonstrating a higher de-identification rate and superior consistency compared to prior approaches in various downstream tasks., Comment: Accepted at AAAI 2024. Paper + supplementary material

Deep networks can be trained to map images into a low-dimensional latent space. In many cases, different images in a collection are articulated versions of one another; for example, same object with different lighting, background, or pose. Furthermore, in many cases, parts of images can be corrupted by noise or missing entries. In this paper, our goal is to recover images without access to the ground-truth (clean) images using the articulations as structural prior of the data. Such recovery problems fall under the domain of compressive sensing. We propose to learn autoencoder with tensor ring factorization on the the embedding space to impose structural constraints on the data. In particular, we use a tensor ring structure in the bottleneck layer of the autoencoder that utilizes the soft labels of the structured dataset. We empirically demonstrate the effectiveness of the proposed approach for inpainting and denoising applications. The resulting method achieves better reconstruction quality compared to other generative prior-based self-supervised recovery approaches for compressive sensing.

Mask-based lensless cameras offer a novel design for imaging systems by replacing the lens in a conventional camera with a layer of coded mask. Each pixel of the lensless camera encodes the information of the entire 3D scene. Existing methods for 3D reconstruction from lensless measurements suffer from poor spatial and depth resolution. This is partially due to the system ill conditioning that arises because the point-spread functions (PSFs) from different depth planes are very similar. In this paper, we propose to capture multiple measurements of the scene under a sequence of coded illumination patterns to improve the 3D image reconstruction quality. In addition, we put the illumination source at a distance away from the camera. With such baseline distance between the lensless camera and illumination source, the camera observes a slice of the 3D volume, and the PSF of each depth plane becomes more resolvable from each other. We present simulation results along with experimental results with a camera prototype to demonstrate the effectiveness of our approach.

Conventional cameras capture image irradiance on a sensor and convert it to RGB images using an image signal processor (ISP). The images can then be used for photography or visual computing tasks in a variety of applications, such as public safety surveillance and autonomous driving. One can argue that since RAW images contain all the captured information, the conversion of RAW to RGB using an ISP is not necessary for visual computing. In this paper, we propose a novel $\rho$-Vision framework to perform high-level semantic understanding and low-level compression using RAW images without the ISP subsystem used for decades. Considering the scarcity of available RAW image datasets, we first develop an unpaired CycleR2R network based on unsupervised CycleGAN to train modular unrolled ISP and inverse ISP (invISP) models using unpaired RAW and RGB images. We can then flexibly generate simulated RAW images (simRAW) using any existing RGB image dataset and finetune different models originally trained for the RGB domain to process real-world camera RAW images. We demonstrate object detection and image compression capabilities in RAW-domain using RAW-domain YOLOv3 and RAW image compressor (RIC) on snapshots from various cameras. Quantitative results reveal that RAW-domain task inference provides better detection accuracy and compression compared to RGB-domain processing. Furthermore, the proposed \r{ho}-Vision generalizes across various camera sensors and different task-specific models. Additional advantages of the proposed $\rho$-Vision that eliminates the ISP are the potential reductions in computations and processing times., Comment: Accepted by T-PAMI 2024. Homepage: https://njuvision.github.io/rho-vision

The majority of methods for crafting adversarial attacks have focused on scenes with a single dominant object (e.g., images from ImageNet). On the other hand, natural scenes include multiple dominant objects that are semantically related. Thus, it is crucial to explore designing attack strategies that look beyond learning on single-object scenes or attack single-object victim classifiers. Due to their inherent property of strong transferability of perturbations to unknown models, this paper presents the first approach of using generative models for adversarial attacks on multi-object scenes. In order to represent the relationships between different objects in the input scene, we leverage upon the open-sourced pre-trained vision-language model CLIP (Contrastive Language-Image Pre-training), with the motivation to exploit the encoded semantics in the language space along with the visual space. We call this attack approach Generative Adversarial Multi-object scene Attacks (GAMA). GAMA demonstrates the utility of the CLIP model as an attacker's tool to train formidable perturbation generators for multi-object scenes. Using the joint image-text features to train the generator, we show that GAMA can craft potent transferable perturbations in order to fool victim classifiers in various attack settings. For example, GAMA triggers ~16% more misclassification than state-of-the-art generative approaches in black-box settings where both the classifier architecture and data distribution of the attacker are different from the victim. Our code is available here: https://abhishekaich27.github.io/gama.html, Comment: Accepted at NeurIPS 2022; First two authors contributed equally; Includes Supplementary Material

State-of-the-art generative model-based attacks against image classifiers overwhelmingly focus on single-object (i.e., single dominant object) images. Different from such settings, we tackle a more practical problem of generating adversarial perturbations using multi-object (i.e., multiple dominant objects) images as they are representative of most real-world scenes. Our goal is to design an attack strategy that can learn from such natural scenes by leveraging the local patch differences that occur inherently in such images (e.g. difference between the local patch on the object `person' and the object `bike' in a traffic scene). Our key idea is to misclassify an adversarial multi-object image by confusing the victim classifier for each local patch in the image. Based on this, we propose a novel generative attack (called Local Patch Difference or LPD-Attack) where a novel contrastive loss function uses the aforesaid local differences in feature space of multi-object scenes to optimize the perturbation generator. Through various experiments across diverse victim convolutional neural networks, we show that our approach outperforms baseline generative attacks with highly transferable perturbations when evaluated under different white-box and black-box settings., Comment: Accepted at WACV 2023 (Round 1), camera-ready version

Blackbox adversarial attacks can be categorized into transfer- and query-based attacks. Transfer methods do not require any feedback from the victim model, but provide lower success rates compared to query-based methods. Query attacks often require a large number of queries for success. To achieve the best of both approaches, recent efforts have tried to combine them, but still require hundreds of queries to achieve high success rates (especially for targeted attacks). In this paper, we propose a novel method for Blackbox Attacks via Surrogate Ensemble Search (BASES) that can generate highly successful blackbox attacks using an extremely small number of queries. We first define a perturbation machine that generates a perturbed image by minimizing a weighted loss function over a fixed set of surrogate models. To generate an attack for a given victim model, we search over the weights in the loss function using queries generated by the perturbation machine. Since the dimension of the search space is small (same as the number of surrogate models), the search requires a small number of queries. We demonstrate that our proposed method achieves better success rate with at least 30x fewer queries compared to state-of-the-art methods on different image classifiers trained with ImageNet. In particular, our method requires as few as 3 queries per image (on average) to achieve more than a 90% success rate for targeted attacks and 1-2 queries per image for over a 99% success rate for untargeted attacks. Our method is also effective on Google Cloud Vision API and achieved a 91% untargeted attack success rate with 2.9 queries per image. We also show that the perturbations generated by our proposed method are highly transferable and can be adopted for hard-label blackbox attacks. We also show effectiveness of BASES for hiding attacks on object detectors., Comment: Our code is available at https://github.com/CSIPlab/BASES

High-speed, high-resolution stereoscopic (H2-Stereo) video allows us to perceive dynamic 3D content at fine granularity. The acquisition of H2-Stereo video, however, remains challenging with commodity cameras. Existing spatial super-resolution or temporal frame interpolation methods provide compromised solutions that lack temporal or spatial details, respectively. To alleviate this problem, we propose a dual camera system, in which one camera captures high-spatial-resolution low-frame-rate (HSR-LFR) videos with rich spatial details, and the other captures low-spatial-resolution high-frame-rate (LSR-HFR) videos with smooth temporal details. We then devise a Learned Information Fusion network (LIFnet) that exploits the cross-camera redundancies to enhance both camera views to high spatiotemporal resolution (HSTR) for reconstructing the H2-Stereo video effectively. We utilize a disparity network to transfer spatiotemporal information across views even in large disparity scenes, based on which, we propose disparity-guided flow-based warping for LSR-HFR view and complementary warping for HSR-LFR view. A multi-scale fusion method in feature domain is proposed to minimize occlusion-induced warping ghosts and holes in HSR-LFR view. The LIFnet is trained in an end-to-end manner using our collected high-quality Stereo Video dataset from YouTube. Extensive experiments demonstrate that our model outperforms existing state-of-the-art methods for both views on synthetic data and camera-captured real data with large disparity. Ablation studies explore various aspects, including spatiotemporal resolution, camera baseline, camera desynchronization, long/short exposures and applications, of our system to fully understand its capability for potential applications.

Incremental Task learning (ITL) is a category of continual learning that seeks to train a single network for multiple tasks (one after another), where training data for each task is only available during the training of that task. Neural networks tend to forget older tasks when they are trained for the newer tasks; this property is often known as catastrophic forgetting. To address this issue, ITL methods use episodic memory, parameter regularization, masking and pruning, or extensible network structures. In this paper, we propose a new incremental task learning framework based on low-rank factorization. In particular, we represent the network weights for each layer as a linear combination of several rank-1 matrices. To update the network for a new task, we learn a rank-1 (or low-rank) matrix and add that to the weights of every layer. We also introduce an additional selector vector that assigns different weights to the low-rank matrices learned for the previous tasks. We show that our approach performs better than the current state-of-the-art methods in terms of accuracy and forgetting. Our method also offers better memory efficiency compared to episodic memory- and mask-based approaches. Our code will be available at https://github.com/CSIPlab/task-increment-rank-update.git, Comment: Code will be available at https://github.com/CSIPlab/task-increment-rank-update.git

Data science and technology offer transformative tools and methods to science. This review article highlights latest development and progress in the interdisciplinary field of data-driven plasma science (DDPS). A large amount of data and machine learning algorithms go hand in hand. Most plasma data, whether experimental, observational or computational, are generated or collected by machines today. It is now becoming impractical for humans to analyze all the data manually. Therefore, it is imperative to train machines to analyze and interpret (eventually) such data as intelligently as humans but far more efficiently in quantity. Despite the recent impressive progress in applications of data science to plasma science and technology, the emerging field of DDPS is still in its infancy. Fueled by some of the most challenging problems such as fusion energy, plasma processing of materials, and fundamental understanding of the universe through observable plasma phenomena, it is expected that DDPS continues to benefit significantly from the interdisciplinary marriage between plasma science and data science into the foreseeable future., Comment: 112 pages (including 700+ references), 44 figures, submitted to IEEE Transactions on Plasma Science as a part of the IEEE Golden Anniversary Special Issue

Sequence diversity is one of the major challenges in the design of diagnostic, prophylactic and therapeutic interventions against viruses. DiMA is a novel tool that is big data-ready and designed to facilitate the dissection of sequence diversity dynamics for viruses. DiMA stands out from other diversity analysis tools by offering various unique features. DiMA provides a quantitative overview of sequence (nucleotide/protein) diversity by use of Shannon's entropy corrected for size bias, applied via a user-defined k-mer sliding window to an input alignment file, and each k-mer position is dissected to various diversity motifs. The motifs are defined based on the probability of distinct sequences at a given k-mer position, whereby an index is the predominant sequence, while all the others are (total) variants to the index. The total variants are sub-classified into the major (most common) variant, minor variants (occurring more than once and of frequency lower than the major), and the unique (singleton) variants. DiMA allows user-defined, sequence metadata enrichment for analyses of the motifs. The application of DiMA was demonstrated for the alignment data of the relatively conserved Spike protein (2,106,985 sequences) of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and the relatively highly diverse Pol protein (3,874) of human immunodeficiency virus-1 (HIV-1). The tool is publicly available as a web server (https://dima.bezmialem.edu.tr), as a Python library (via PyPi) and as a command line client (Via GitHub)., Comment: 18 pages, 2 figures, 50 references

The event camera's low power consumption and ability to capture microsecond brightness changes make it attractive for various computer vision tasks. Existing event representation methods typically convert events into frames, voxel grids, or spikes for deep neural networks (DNNs). However, these approaches often sacrifice temporal granularity or require specialized devices for processing. This work introduces a novel token-based event representation, where each event is considered a fundamental processing unit termed an event-token. This approach preserves the sequence's intricate spatiotemporal attributes at the event level. Moreover, we propose a Three-way Attention mechanism in the Event Transformer Block (ETB) to collaboratively construct temporal and spatial correlations between events. We compare our proposed token-based event representation extensively with other prevalent methods for object classification and optical flow estimation. The experimental results showcase its competitive performance while demanding minimal computational resources on standard devices. Our code is publicly accessible at \url{https://github.com/NJUVISION/EventTransformer}., Comment: Accepted by ICASSP2024

Adversarial attacks perturb images such that a deep neural network produces incorrect classification results. A promising approach to defend against adversarial attacks on natural multi-object scenes is to impose a context-consistency check, wherein, if the detected objects are not consistent with an appropriately defined context, then an attack is suspected. Stronger attacks are needed to fool such context-aware detectors. We present the first approach for generating context-consistent adversarial attacks that can evade the context-consistency check of black-box object detectors operating on complex, natural scenes. Unlike many black-box attacks that perform repeated attempts and open themselves to detection, we assume a "zero-query" setting, where the attacker has no knowledge of the classification decisions of the victim system. First, we derive multiple attack plans that assign incorrect labels to victim objects in a context-consistent manner. Then we design and use a novel data structure that we call the perturbation success probability matrix, which enables us to filter the attack plans and choose the one most likely to succeed. This final attack plan is implemented using a perturbation-bounded adversarial attack algorithm. We compare our zero-query attack against a few-query scheme that repeatedly checks if the victim system is fooled. We also compare against state-of-the-art context-agnostic attacks. Against a context-aware defense, the fooling rate of our zero-query approach is significantly higher than context-agnostic approaches and higher than that achievable with up to three rounds of the few-query scheme., Comment: CVPR 2022 Accepted

In continual learning (CL), the goal is to design models that can learn a sequence of tasks without catastrophic forgetting. While there is a rich set of techniques for CL, relatively little understanding exists on how representations built by previous tasks benefit new tasks that are added to the network. To address this, we study the problem of continual representation learning (CRL) where we learn an evolving representation as new tasks arrive. Focusing on zero-forgetting methods where tasks are embedded in subnetworks (e.g., PackNet), we first provide experiments demonstrating CRL can significantly boost sample efficiency when learning new tasks. To explain this, we establish theoretical guarantees for CRL by providing sample complexity and generalization error bounds for new tasks by formalizing the statistical benefits of previously-learned representations. Our analysis and experiments also highlight the importance of the order in which we learn the tasks. Specifically, we show that CL benefits if the initial tasks have large sample size and high "representation diversity". Diversity ensures that adding new tasks incurs small representation mismatch and can be learned with few samples while training only few additional nonzero weights. Finally, we ask whether one can ensure each task subnetwork to be efficient during inference time while retaining the benefits of representation learning. To this end, we propose an inference-efficient variation of PackNet called Efficient Sparse PackNet (ESPN) which employs joint channel & weight pruning. ESPN embeds tasks in channel-sparse subnets requiring up to 80% less FLOPs to compute while approximately retaining accuracy and is very competitive with a variety of baselines. In summary, this work takes a step towards data and compute-efficient CL with a representation learning perspective. GitHub page: https://github.com/ucr-optml/CtRL

Blackbox transfer attacks for image classifiers have been extensively studied in recent years. In contrast, little progress has been made on transfer attacks for object detectors. Object detectors take a holistic view of the image and the detection of one object (or lack thereof) often depends on other objects in the scene. This makes such detectors inherently context-aware and adversarial attacks in this space are more challenging than those targeting image classifiers. In this paper, we present a new approach to generate context-aware attacks for object detectors. We show that by using co-occurrence of objects and their relative locations and sizes as context information, we can successfully generate targeted mis-categorization attacks that achieve higher transfer success rates on blackbox object detectors than the state-of-the-art. We test our approach on a variety of object detectors with images from PASCAL VOC and MS COCO datasets and demonstrate up to $20$ percentage points improvement in performance compared to the other state-of-the-art methods., Comment: accepted to AAAI 2022

Mask-based lensless cameras can be flat, thin, and light-weight, which makes them suitable for novel designs of computational imaging systems with large surface areas and arbitrary shapes. Despite recent progress in lensless cameras, the quality of images recovered from the lensless cameras is often poor due to the ill-conditioning of the underlying measurement system. In this paper, we propose to use coded illumination to improve the quality of images reconstructed with lensless cameras. In our imaging model, the scene/object is illuminated by multiple coded illumination patterns as the lensless camera records sensor measurements. We designed and tested a number of illumination patterns and observed that shifting dots (and related orthogonal) patterns provide the best overall performance. We propose a fast and low-complexity recovery algorithm that exploits the separability and block-diagonal structure in our system. We present simulation results and hardware experiment results to demonstrate that our proposed method can significantly improve the reconstruction quality., Comment: Supplementary material, codes, and data are available at https://github.com/CSIPlab/codedcam

Deep Neural Networks (DNNs) have been shown to be vulnerable to adversarial examples, which are slightly perturbed input images which lead DNNs to make wrong predictions. To protect from such examples, various defense strategies have been proposed. A very recent defense strategy for detecting adversarial examples, that has been shown to be robust to current attacks, is to check for intrinsic context consistencies in the input data, where context refers to various relationships (e.g., object-to-object co-occurrence relationships) in images. In this paper, we show that even context consistency checks can be brittle to properly crafted adversarial examples and to the best of our knowledge, we are the first to do so. Specifically, we propose an adaptive framework to generate examples that subvert such defenses, namely, Adversarial attacks against object Detection that evade Context consistency checks (ADC). In ADC, we formulate a joint optimization problem which has two attack goals, viz., (i) fooling the object detector and (ii) evading the context consistency check system, at the same time. Experiments on both PASCAL VOC and MS COCO datasets show that examples generated with ADC fool the object detector with a success rate of over 85% in most cases, and at the same time evade the recently proposed context consistency checks, with a bypassing rate of over 80% in most cases. Our results suggest that how to robustly model context and check its consistency, is still an open problem., Comment: WCAV'22 Acceptted

When compared to the image classification models, black-box adversarial attacks against video classification models have been largely understudied. This could be possible because, with video, the temporal dimension poses significant additional challenges in gradient estimation. Query-efficient black-box attacks rely on effectively estimated gradients towards maximizing the probability of misclassifying the target video. In this work, we demonstrate that such effective gradients can be searched for by parameterizing the temporal structure of the search space with geometric transformations. Specifically, we design a novel iterative algorithm Geometric TRAnsformed Perturbations (GEO-TRAP), for attacking video classification models. GEO-TRAP employs standard geometric transformation operations to reduce the search space for effective gradients into searching for a small group of parameters that define these operations. This group of parameters describes the geometric progression of gradients, resulting in a reduced and structured search space. Our algorithm inherently leads to successful perturbations with surprisingly few queries. For example, adversarial examples generated from GEO-TRAP have better attack success rates with ~73.55% fewer queries compared to the state-of-the-art method for video adversarial attacks on the widely used Jester dataset. Overall, our algorithm exposes vulnerabilities of diverse video classification models and achieves new state-of-the-art results under black-box settings on two large datasets. Code is available here: https://github.com/sli057/Geo-TRAP, Comment: Accepted at NeurIPS 2021; First two authors contributed equally; Includes Supplementary Material

Vision systems that deploy Deep Neural Networks (DNNs) are known to be vulnerable to adversarial examples. Recent research has shown that checking the intrinsic consistencies in the input data is a promising way to detect adversarial attacks (e.g., by checking the object co-occurrence relationships in complex scenes). However, existing approaches are tied to specific models and do not offer generalizability. Motivated by the observation that language descriptions of natural scene images have already captured the object co-occurrence relationships that can be learned by a language model, we develop a novel approach to perform context consistency checks using such language models. The distinguishing aspect of our approach is that it is independent of the deployed object detector and yet offers very high accuracy in terms of detecting adversarial examples in practical scenes with multiple objects., Comment: ICCV'21 Accepted

Lensless cameras provide a framework to build thin imaging systems by replacing the lens in a conventional camera with an amplitude or phase mask near the sensor. Existing methods for lensless imaging can recover the depth and intensity of the scene, but they require solving computationally-expensive inverse problems. Furthermore, existing methods struggle to recover dense scenes with large depth variations. In this paper, we propose a lensless imaging system that captures a small number of measurements using different patterns on a programmable mask. In this context, we make three contributions. First, we present a fast recovery algorithm to recover textures on a fixed number of depth planes in the scene. Second, we consider the mask design problem, for programmable lensless cameras, and provide a design template for optimizing the mask patterns with the goal of improving depth estimation. Third, we use a refinement network as a post-processing step to identify and remove artifacts in the reconstruction. These modifications are evaluated extensively with experimental results on a lensless camera prototype to showcase the performance benefits of the optimized masks and recovery algorithms over the state of the art., Comment: Supplementary material available at https://github.com/CSIPlab/Programmable3Dcam.git

The plug-and-play priors (PnP) and regularization by denoising (RED) methods have become widely used for solving inverse problems by leveraging pre-trained deep denoisers as image priors. While the empirical imaging performance and the theoretical convergence properties of these algorithms have been widely investigated, their recovery properties have not previously been theoretically analyzed. We address this gap by showing how to establish theoretical recovery guarantees for PnP/RED by assuming that the solution of these methods lies near the fixed-points of a deep neural network. We also present numerical results comparing the recovery performance of PnP/RED in compressive sensing against that of recent compressive sensing algorithms based on generative models. Our numerical results suggest that PnP with a pre-trained artifact removal network provides significantly better results compared to the existing state-of-the-art methods., Comment: 27 pages, 13 figures

The traditional approach of hand-crafting priors (such as sparsity) for solving inverse problems is slowly being replaced by the use of richer learned priors (such as those modeled by deep generative networks). In this work, we study the algorithmic aspects of such a learning-based approach from a theoretical perspective. For certain generative network architectures, we establish a simple non-convex algorithmic approach that (a) theoretically enjoys linear convergence guarantees for certain linear and nonlinear inverse problems, and (b) empirically improves upon conventional techniques such as back-propagation. We support our claims with the experimental results for solving various inverse problems. We also propose an extension of our approach that can handle model mismatch (i.e., situations where the generative network prior is not exactly applicable). Together, our contributions serve as building blocks towards a principled use of generative models in inverse problems with more complete algorithmic understanding., Comment: arXiv admin note: text overlap with arXiv:1810.03587, arXiv:1802.08406

Fourier phase retrieval is a classical problem that deals with the recovery of an image from the amplitude measurements of its Fourier coefficients. Conventional methods solve this problem via iterative (alternating) minimization by leveraging some prior knowledge about the structure of the unknown image. The inherent ambiguities about shift and flip in the Fourier measurements make this problem especially difficult; and most of the existing methods use several random restarts with different permutations. In this paper, we assume that a known (learned) reference is added to the signal before capturing the Fourier amplitude measurements. Our method is inspired by the principle of adding a reference signal in holography. To recover the signal, we implement an iterative phase retrieval method as an unrolled network. Then we use back propagation to learn the reference that provides us the best reconstruction for a fixed number of phase retrieval iterations. We performed a number of simulations on a variety of datasets under different conditions and found that our proposed method for phase retrieval via unrolled network and learned reference provides near-perfect recovery at fixed (small) computational cost. We compared our method with standard Fourier phase retrieval methods and observed significant performance enhancement using the learned reference., Comment: Accepted to ECCV 2020. Code is available at https://github.com/CSIPlab/learnPR_reference

Signal recovery from nonlinear measurements involves solving an iterative optimization problem. In this paper, we present a framework to optimize the sensing parameters to improve the quality of the signal recovered by the given iterative method. In particular, we learn illumination patterns to recover signals from coded diffraction patterns using a fixed-cost alternating minimization-based phase retrieval method. Coded diffraction phase retrieval is a physically realistic system in which the signal is first modulated by a sequence of codes before the sensor records its Fourier amplitude. We represent the phase retrieval method as an unrolled network with a fixed number of layers and minimize the recovery error by optimizing over the measurement parameters. Since the number of iterations/layers are fixed, the recovery incurs a fixed cost. We present extensive simulation results on a variety of datasets under different conditions and a comparison with existing methods. Our results demonstrate that the proposed method provides near-perfect reconstruction using patterns learned with a small number of training images. Our proposed method provides significant improvements over existing methods both in terms of accuracy and speed.

Most of the existing works in video synthesis focus on generating videos using adversarial learning. Despite their success, these methods often require input reference frame or fail to generate diverse videos from the given data distribution, with little to no uniformity in the quality of videos that can be generated. Different from these methods, we focus on the problem of generating videos from latent noise vectors, without any reference input frames. To this end, we develop a novel approach that jointly optimizes the input latent space, the weights of a recurrent neural network and a generator through non-adversarial learning. Optimizing for the input latent space along with the network weights allows us to generate videos in a controlled environment, i.e., we can faithfully generate all videos the model has seen during the learning process as well as new unseen videos. Extensive experiments on three challenging and diverse datasets well demonstrate that our approach generates superior quality videos compared to the existing state-of-the-art methods., Comment: Accepted to CVPR 2020

Mask-based lensless cameras replace the lens of a conventional camera with a custom mask. These cameras can potentially be very thin and even flexible. Recently, it has been demonstrated that such mask-based cameras can recover light intensity and depth information of a scene. Existing depth recovery algorithms either assume that the scene consists of a small number of depth planes or solve a sparse recovery problem over a large 3D volume. Both these approaches fail to recover the scenes with large depth variations. In this paper, we propose a new approach for depth estimation based on an alternating gradient descent algorithm that jointly estimates a continuous depth map and light distribution of the unknown scene from its lensless measurements. We present simulation results on image and depth reconstruction for a variety of 3D test scenes. A comparison between the proposed algorithm and other method shows that our algorithm is more robust for natural scenes with a large range of depths. We built a prototype lensless camera and present experimental results for reconstruction of intensity and depth maps of different real objects., Comment: Added new experiments with camera prototype

This paper presents a dual camera system for high spatiotemporal resolution (HSTR) video acquisition, where one camera shoots a video with high spatial resolution and low frame rate (HSR-LFR) and another one captures a low spatial resolution and high frame rate (LSR-HFR) video. Our main goal is to combine videos from LSR-HFR and HSR-LFR cameras to create an HSTR video. We propose an end-to-end learning framework, AWnet, mainly consisting of a FlowNet and a FusionNet that learn an adaptive weighting function in pixel domain to combine inputs in a frame recurrent fashion. To improve the reconstruction quality for cameras used in reality, we also introduce noise regularization under the same framework. Our method has demonstrated noticeable performance gains in terms of both objective PSNR measurement in simulation with different publicly available video and light-field datasets and subjective evaluation with real data captured by dual iPhone 7 and Grasshopper3 cameras. Ablation studies are further conducted to investigate and explore various aspects (such as reference structure, camera parallax, exposure time, etc) of our system to fully understand its capability for potential applications., Comment: To appear in IEEE Transactions on Pattern Analysis and Machine Intelligence

The classical problem of phase retrieval arises in various signal acquisition systems. Due to the ill-posed nature of the problem, the solution requires assumptions on the structure of the signal. In the last several years, sparsity and support-based priors have been leveraged successfully to solve this problem. In this work, we propose replacing the sparsity/support priors with generative priors and propose two algorithms to solve the phase retrieval problem. Our proposed algorithms combine the ideas from AltMin approach for non-convex sparse phase retrieval and projected gradient descent approach for solving linear inverse problems using generative priors. We empirically show that the performance of our method with projected gradient descent is superior to the existing approach for solving phase retrieval under generative priors. We support our method with an analysis of sample complexity with Gaussian measurements., Comment: Published in ICASSP 2019

Finding compact representation of videos is an essential component in almost every problem related to video processing or understanding. In this paper, we propose a generative model to learn compact latent codes that can efficiently represent and reconstruct a video sequence from its missing or under-sampled measurements. We use a generative network that is trained to map a compact code into an image. We first demonstrate that if a video sequence belongs to the range of the pretrained generative network, then we can recover it by estimating the underlying compact latent codes. Then we demonstrate that even if the video sequence does not belong to the range of a pretrained network, we can still recover the true video sequence by jointly updating the latent codes and the weights of the generative network. To avoid overfitting in our model, we regularize the recovery problem by imposing low-rank and similarity constraints on the latent codes of the neighboring frames in the video sequence. We use our methods to recover a variety of videos from compressive measurements at different compression rates. We also demonstrate that we can generate missing frames in a video sequence by interpolating the latent codes of the observed frames in the low-dimensional space.

We consider the phase retrieval problem for signals that belong to a union of subspaces. We assume that amplitude measurements of the signal of length $n$ are observed after passing it through a random $m \times n$ measurement matrix. We also assume that the signal belongs to the span of a single $d$-dimensional subspace out of $R$ subspaces, where $d\ll n$. We assume the knowledge of all possible subspaces, but the true subspace of the signal is unknown. We present an algorithm that jointly estimates the phase of the measurements and the subspace support of the signal. We discuss theoretical guarantees on the recovery of signals and present simulation results to demonstrate the empirical performance of our proposed algorithm. Our main result suggests that if properly initialized, then $O(d+\log R)$ random measurements are sufficient for phase retrieval if the unknown signal belongs to the union of $R$ low-dimensional subspaces., Comment: working draft

Recently, coded masks have been used to demonstrate a thin form-factor lensless camera, FlatCam, in which a mask is placed immediately on top of a bare image sensor. In this paper, we present an imaging model and algorithm to jointly estimate depth and intensity information in the scene from a single or multiple FlatCams. We use a light field representation to model the mapping of 3D scene onto the sensor in which light rays from different depths yield different modulation patterns. We present a greedy depth pursuit algorithm to search the 3D volume and estimate the depth and intensity of each pixel within the camera field-of-view. We present simulation results to analyze the performance of our proposed model and algorithm with different FlatCam settings.

In this work, we propose using camera arrays coupled with coherent illumination as an effective method of improving spatial resolution in long distance images by a factor of ten and beyond. Recent advances in ptychography have demonstrated that one can image beyond the diffraction limit of the objective lens in a microscope. We demonstrate a similar imaging system to image beyond the diffraction limit in long range imaging. We emulate a camera array with a single camera attached to an X-Y translation stage. We show that an appropriate phase retrieval based reconstruction algorithm can be used to effectively recover the lost high resolution details from the multiple low resolution acquired images. We analyze the effects of noise, required degree of image overlap, and the effect of increasing synthetic aperture size on the reconstructed image quality. We show that coherent camera arrays have the potential to greatly improve imaging performance. Our simulations show resolution gains of 10x and more are achievable. Furthermore, experimental results from our proof-of-concept systems show resolution gains of 4x-7x for real scenes. Finally, we introduce and analyze in simulation a new strategy to capture macroscopic Fourier Ptychography images in a single snapshot, albeit using a camera array., Comment: 13 pages, 16 figures, submitted to IEEE Transactions on Computational Imaging

Kernels are executable code segments and kernel fusion is a technique for combing the segments in a coherent manner to improve execution time. For the first time, we have developed a technique to fuse image processing kernels to be executed on GPGPUs for improving execution time and total throughput (amount of data processed in unit time). We have applied our techniques for feature tracking on video images captured by a high speed digital video camera where the number of frames captured varies between 600-1000 frames per second. Image processing kernels are composed of multiple simple kernels, which executes on the input image in a given sequence. A set of kernels that can be fused together forms a partition (or fused kernel). Given a set of Kernels and the data dependencies between them, it is difficult to determine the partitions of kernels such that the total performance is maximized (execution time and throughput). We have developed and implemented an optimization model to find such a partition. We also developed an algorithm to fuse multiple kernels based on their data dependencies. Additionally, to further improve performance on GPGPU systems, we have provided methods to distribute data and threads to processors. Our model was able to reduce data traffic, which resulted better performance.The performance (both execution time and throughput) of the proposed method for kernel fusing and its subsequent execution is shown to be 2 to 3 times higher than executing kernels in sequence. We have demonstrated our technique for facial feature tracking with applications to Neuroscience.