Search

Following the success in NLP, the best vision models are now in the billion parameter ranges. Adapting these large models to a target distribution has become computationally and economically prohibitive. Addressing this challenge, we introduce UpStep, an Unsupervised Parameter-efficient Source-free post-pretraining approach, designed to efficiently adapt a base model from a source domain to a target domain: i) we design a self-supervised training scheme to adapt a pretrained model on an unlabeled target domain in a setting where source domain data is unavailable. Such source-free setting comes with the risk of catastrophic forgetting, hence, ii) we propose center vector regularization (CVR), a set of auxiliary operations that minimize catastrophic forgetting and additionally reduces the computational cost by skipping backpropagation in 50\% of the training iterations. Finally iii) we perform this adaptation process in a parameter-efficient way by adapting the pretrained model through low-rank adaptation methods, resulting in a fraction of parameters to optimize. We utilize various general backbone architectures, both supervised and unsupervised, trained on Imagenet as our base model and adapt them to a diverse set of eight target domains demonstrating the adaptability and generalizability of our proposed approach.

Bulk two dimensional (2D) superconductivity has gained considerable attention due to its intricate interplay between symmetry breaking, nontrivial topology, 2D phase fluctuations, and unconventional superconductivity. However, certain intercalated layered superconductors, despite their short c-axis superconducting coherence length, have been misclassified as anisotropic three-dimensional (3D) superconductors. Here, we investigate (Li,Fe)OHFeSe superconductors with varying degrees of interlayer misalignment, revealing sample-dependent superconducting dimensionality while consistently observing Berezinskii Kosterlitz Thouless (BKT) transitions. To resolve this discrepancy, we develop an extended 2D Tinkham model that quantitatively captures the blurring effects induced by interlayer misalignment. We further demonstrate the validity of this model in both (Li,Fe)OHFeSe and cetyltrimethyl ammonium (CTA+) intercalated (CTA)0.5SnSe2 superconductors, highlighting its broad applicability. This work provides valuable insights into bulk 2D superconductivity and establishes an extended 2D Tinkham model for quantitatively extracting intrinsic superconducting properties in intercalated layered superconductors, particularly those exhibiting significant interlayer misalignments.

Zero-shot recognition models require extensive training data for generalization. However, in zero-shot 3D classification, collecting 3D data and captions is costly and laborintensive, posing a significant barrier compared to 2D vision. Recent advances in generative models have achieved unprecedented realism in synthetic data production, and recent research shows the potential for using generated data as training data. Here, naturally raising the question: Can synthetic 3D data generated by generative models be used as expanding limited 3D datasets? In response, we present a synthetic 3D dataset expansion method, Textguided Geometric Augmentation (TeGA). TeGA is tailored for language-image-3D pretraining, which achieves SoTA in zero-shot 3D classification, and uses a generative textto-3D model to enhance and extend limited 3D datasets. Specifically, we automatically generate text-guided synthetic 3D data and introduce a consistency filtering strategy to discard noisy samples where semantics and geometric shapes do not match with text. In the experiment to double the original dataset size using TeGA, our approach demonstrates improvements over the baselines, achieving zeroshot performance gains of 3.0% on Objaverse-LVIS, 4.6% on ScanObjectNN, and 8.7% on ModelNet40. These results demonstrate that TeGA effectively bridges the 3D data gap, enabling robust zero-shot 3D classification even with limited real training data and paving the way for zero-shot 3D vision application.

Symmetry elegantly governs the fundamental properties and derived functionalities of condensed matter. For instance, realizing the superconducting diode effect (SDE) demands breaking space-inversion and time-reversal symmetries simultaneously. Although the SDE is widely observed in various platforms, its underlying mechanism remains debated, particularly regarding the role of vortices. Here, we systematically investigate the nonreciprocal transport in the chiral type-I superconductor NbGe2. Moreover, we induce type-II superconductivity with elevated superconducting critical temperature on the artificial surface by focused ion beam irradiation, enabling control over vortex dynamics in NbGe2 devices. Strikingly, we observe negligible diode efficiency (Q < 2%) at low magnetic fields, which rises significantly to Q ~ 50% at high magnetic fields, coinciding with an abrupt increase in vortex creep rate when the superconductivity of NbGe2 bulk is suppressed. These results unambiguously highlight the critical role of vortex dynamics in the SDE, in addition to the established symmetry rules.

In the realm of novelty detection, accurately identifying outliers in data without specific class information poses a significant challenge. While current methods excel in single-object scenarios, they struggle with multi-object situations due to their focus on individual objects. Our paper suggests a novel approach: redefining `normal' at the object level in training datasets. Rather than the usual image-level view, we consider the most dominant object in a dataset as the norm, offering a perspective that is more effective for real-world scenarios. Adapting to our object-level definition of `normal', we modify knowledge distillation frameworks, where a student network learns from a pre-trained teacher network. Our first contribution, DeFeND(Dense Feature Fine-tuning on Normal Data), integrates dense feature fine-tuning into the distillation process, allowing the teacher network to focus on object-level features with a self-supervised loss. The second is masked knowledge distillation, where the student network works with partially hidden inputs, honing its ability to deduce and generalize from incomplete data. This approach not only fares well in single-object novelty detection but also considerably surpasses existing methods in multi-object contexts. The implementation is available at: https://github.com/SMSD75/Redefining_Normal_ACCV24/tree/main, Comment: Accepted at ACCV24(Oral)

Spatial awareness is key to enable embodied multimodal AI systems. Yet, without vast amounts of spatial supervision, current Visual Language Models (VLMs) struggle at this task. In this paper, we introduce LynX, a framework that equips pretrained VLMs with visual grounding ability without forgetting their existing image and language understanding skills. To this end, we propose a Dual Mixture of Experts module that modifies only the decoder layer of the language model, using one frozen Mixture of Experts (MoE) pre-trained on image and language understanding and another learnable MoE for new grounding capabilities. This allows the VLM to retain previously learned knowledge and skills, while acquiring what is missing. To train the model effectively, we generate a high-quality synthetic dataset we call SCouT, which mimics human reasoning in visual grounding. This dataset provides rich supervision signals, describing a step-by-step multimodal reasoning process, thereby simplifying the task of visual grounding. We evaluate LynX on several object detection and visual grounding datasets, demonstrating strong performance in object detection, zero-shot localization and grounded reasoning while maintaining its original image and language understanding capabilities on seven standard benchmark datasets.

We address the challenge of representing long captions in vision-language models, such as CLIP. By design these models are limited by fixed, absolute positional encodings, restricting inputs to a maximum of 77 tokens and hindering performance on tasks requiring longer descriptions. Although recent work has attempted to overcome this limit, their proposed approaches struggle to model token relationships over longer distances and simply extend to a fixed new token length. Instead, we propose a generalizable method, named TULIP, able to upgrade the token length to any length for CLIP-like models. We do so by improving the architecture with relative position encodings, followed by a training procedure that (i) distills the original CLIP text encoder into an encoder with relative position encodings and (ii) enhances the model for aligning longer captions with images. By effectively encoding captions longer than the default 77 tokens, our model outperforms baselines on cross-modal tasks such as retrieval and text-to-image generation.

Large language models have demonstrated impressive performance when integrated with vision models even enabling video understanding. However, evaluating these video models presents its own unique challenges, for which several benchmarks have been proposed. In this paper, we show that the currently most used video-language benchmarks can be solved without requiring much temporal reasoning. We identified three main issues in existing datasets: (i) static information from single frames is often sufficient to solve the tasks (ii) the text of the questions and candidate answers is overly informative, allowing models to answer correctly without relying on any visual input (iii) world knowledge alone can answer many of the questions, making the benchmarks a test of knowledge replication rather than visual reasoning. In addition, we found that open-ended question-answering benchmarks for video understanding suffer from similar issues while the automatic evaluation process with LLMs is unreliable, making it an unsuitable alternative. As a solution, we propose TVBench, a novel open-source video multiple-choice question-answering benchmark, and demonstrate through extensive evaluations that it requires a high level of temporal understanding. Surprisingly, we find that most recent state-of-the-art video-language models perform similarly to random performance on TVBench, with only a few models such as Qwen2-VL, and Tarsier clearly surpassing this baseline.

How well do text-only Large Language Models (LLMs) naturally align with the visual world? We provide the first direct analysis by utilizing frozen text representations in a discriminative vision-language model framework and measuring zero-shot generalization on unseen classes. We find decoder-based LLMs exhibit high intrinsic visual alignment. In particular, more capable LLMs reliably demonstrate stronger generalization. Moreover, utilizing frozen LLMs leads to strong gains in cross-lingual settings, where our approach surpasses CLIP's accuracy of 1.4% with 38.7% for Chinese. Our proposed method improves both robustness and generalization and also significantly reduces the need for paired data and compute, making vision-language models more accessible and adaptable.

With the advent of billion-parameter foundation models, efficient fine-tuning has become increasingly important for the adaptation of models to downstream tasks. However, especially in computer vision, it can be hard to achieve good performance when access to quality labeled data is lacking. In this work, we propose a method adapting pretrained generalist models in a self-supervised manner by learning binary masks. These self-supervised masking networks (SMNs) are up to 79x more efficient to store and significantly improve performance on label-efficient downstream tasks. We validate the usefulness of learning binary masks as a fine-tuning method on 8 datasets and 3 model architectures, and we demonstrate the effectiveness of SMNs in 3 label-efficient settings., Comment: Oral at GCPR'24, code at https://github.com/alvitawa/UnsupervisedMasking

Foundation models (FMs) are a popular topic of research in AI. Their ability to generalize to new tasks and datasets without retraining or needing an abundance of data makes them an appealing candidate for applications on specialist datasets. In this work, we compare the performance of FMs to finetuned pre-trained supervised models in the task of semantic segmentation on an entirely new dataset. We see that finetuned models consistently outperform the FMs tested, even in cases were data is scarce. We release the code and dataset for this work on GitHub., Comment: Accepted at ECCV 2024 Green Foundation Models workshop

In this work, we investigate the understudied effect of the training data used for image super-resolution (SR). Most commonly, novel SR methods are developed and benchmarked on common training datasets such as DIV2K and DF2K. However, we investigate and rethink the training data from the perspectives of diversity and quality, {thereby addressing the question of ``How important is SR training for SR models?''}. To this end, we propose an automated image evaluation pipeline. With this, we stratify existing high-resolution image datasets and larger-scale image datasets such as ImageNet and PASS to compare their performances. We find that datasets with (i) low compression artifacts, (ii) high within-image diversity as judged by the number of different objects, and (iii) a large number of images from ImageNet or PASS all positively affect SR performance. We hope that the proposed simple-yet-effective dataset curation pipeline will inform the construction of SR datasets in the future and yield overall better models., Comment: Accepted to ECCV2024

In this paper, we address Generalized Category Discovery, aiming to simultaneously uncover novel categories and accurately classify known ones. Traditional methods, which lean heavily on self-supervision and contrastive learning, often fall short when distinguishing between fine-grained categories. To address this, we introduce a novel concept called `self-expertise', which enhances the model's ability to recognize subtle differences and uncover unknown categories. Our approach combines unsupervised and supervised self-expertise strategies to refine the model's discernment and generalization. Initially, hierarchical pseudo-labeling is used to provide `soft supervision', improving the effectiveness of self-expertise. Our supervised technique differs from traditional methods by utilizing more abstract positive and negative samples, aiding in the formation of clusters that can generalize to novel categories. Meanwhile, our unsupervised strategy encourages the model to sharpen its category distinctions by considering within-category examples as `hard' negatives. Supported by theoretical insights, our empirical results showcase that our method outperforms existing state-of-the-art techniques in Generalized Category Discovery across several fine-grained datasets. Our code is available at: https://github.com/SarahRastegar/SelEx., Comment: Accepted by ECCV 2024

We introduce NeCo: Patch Neighbor Consistency, a novel self-supervised training loss that enforces patch-level nearest neighbor consistency across a student and teacher model. Compared to contrastive approaches that only yield binary learning signals, i.e., 'attract' and 'repel', this approach benefits from the more fine-grained learning signal of sorting spatially dense features relative to reference patches. Our method leverages differentiable sorting applied on top of pretrained representations, such as DINOv2-registers to bootstrap the learning signal and further improve upon them. This dense post-pretraining leads to superior performance across various models and datasets, despite requiring only 19 hours on a single GPU. This method generates high-quality dense feature encoders and establishes several new state-of-the-art results such as +5.5% and +6% for non-parametric in-context semantic segmentation on ADE20k and Pascal VOC, +7.2% and +5.7% for linear segmentation evaluations on COCO-Things and -Stuff and improvements in the 3D understanding of multi-view consistency on SPair-71k, by more than 1.5%., Comment: Accepted at ICLR25. The webpage is accessible at: https://vpariza.github.io/NeCo/

Pre-training and transfer learning are an important building block of current computer vision systems. While pre-training is usually performed on large real-world image datasets, in this paper we ask whether this is truly necessary. To this end, we search for a minimal, purely synthetic pre-training dataset that allows us to achieve performance similar to the 1 million images of ImageNet-1k. We construct such a dataset from a single fractal with perturbations. With this, we contribute three main findings. (i) We show that pre-training is effective even with minimal synthetic images, with performance on par with large-scale pre-training datasets like ImageNet-1k for full fine-tuning. (ii) We investigate the single parameter with which we construct artificial categories for our dataset. We find that while the shape differences can be indistinguishable to humans, they are crucial for obtaining strong performances. (iii) Finally, we investigate the minimal requirements for successful pre-training. Surprisingly, we find that a substantial reduction of synthetic images from 1k to 1 can even lead to an increase in pre-training performance, a motivation to further investigate ''scaling backwards''. Finally, we extend our method from synthetic images to real images to see if a single real image can show similar pre-training effect through shape augmentation. We find that the use of grayscale images and affine transformations allows even real images to ''scale backwards''., Comment: Accepted to ECCV2024

Video-based pretraining offers immense potential for learning strong visual representations on an unprecedented scale. Recently, masked video modeling methods have shown promising scalability, yet fall short in capturing higher-level semantics due to reconstructing predefined low-level targets such as pixels. To tackle this, we present Sinkhorn-guided Masked Video Modelling (SIGMA), a novel video pretraining method that jointly learns the video model in addition to a target feature space using a projection network. However, this simple modification means that the regular L2 reconstruction loss will lead to trivial solutions as both networks are jointly optimized. As a solution, we distribute features of space-time tubes evenly across a limited number of learnable clusters. By posing this as an optimal transport problem, we enforce high entropy in the generated features across the batch, infusing semantic and temporal meaning into the feature space. The resulting cluster assignments are used as targets for a symmetric prediction task where the video model predicts cluster assignment of the projection network and vice versa. Experimental results on ten datasets across three benchmarks validate the effectiveness of SIGMA in learning more performant, temporally-aware, and robust video representations improving upon state-of-the-art methods. Our project website with code is available at: https://quva-lab.github.io/SIGMA., Comment: Accepted at ECCV 24

In the domain of anomaly detection, methods often excel in either high-level semantic or low-level industrial benchmarks, rarely achieving cross-domain proficiency. Semantic anomalies are novelties that differ in meaning from the training set, like unseen objects in self-driving cars. In contrast, industrial anomalies are subtle defects that preserve semantic meaning, such as cracks in airplane components. In this paper, we present GeneralAD, an anomaly detection framework designed to operate in semantic, near-distribution, and industrial settings with minimal per-task adjustments. In our approach, we capitalize on the inherent design of Vision Transformers, which are trained on image patches, thereby ensuring that the last hidden states retain a patch-based structure. We propose a novel self-supervised anomaly generation module that employs straightforward operations like noise addition and shuffling to patch features to construct pseudo-abnormal samples. These features are fed to an attention-based discriminator, which is trained to score every patch in the image. With this, our method can both accurately identify anomalies at the image level and also generate interpretable anomaly maps. We extensively evaluated our approach on ten datasets, achieving state-of-the-art results in six and on-par performance in the remaining for both localization and detection tasks., Comment: Accepted at ECCV 2024

This paper introduces FUNGI, Features from UNsupervised GradIents, a method to enhance the features of transformer encoders by leveraging self-supervised gradients. Our method is simple: given any pretrained model, we first compute gradients from various self-supervised objectives for each input. These gradients are projected to a lower dimension and then concatenated with the model's output embedding. The resulting features are evaluated on k-nearest neighbor classification over 11 datasets from vision, 5 from natural language processing, and 2 from audio. Across backbones spanning various sizes and pretraining strategies, FUNGI features provide consistent performance improvements over the embeddings. We also show that using FUNGI features can benefit linear classification, clustering and image retrieval, and that they significantly improve the retrieval-based in-context scene understanding abilities of pretrained models, for example improving upon DINO by +17% for semantic segmentation - without any training., Comment: NeurIPS 2024. Code available at https://github.com/WalterSimoncini/fungivision

Federated Learning (FL) enables multiple machines to collaboratively train a machine learning model without sharing of private training data. Yet, especially for heterogeneous models, a key bottleneck remains the transfer of knowledge gained from each client model with the server. One popular method, FedDF, uses distillation to tackle this task with the use of a common, shared dataset on which predictions are exchanged. However, in many contexts such a dataset might be difficult to acquire due to privacy and the clients might not allow for storage of a large shared dataset. To this end, in this paper, we introduce a new method that improves this knowledge distillation method to only rely on a single shared image between clients and server. In particular, we propose a novel adaptive dataset pruning algorithm that selects the most informative crops generated from only a single image. With this, we show that federated learning with distillation under a limited shared dataset budget works better by using a single image compared to multiple individual ones. Finally, we extend our approach to allow for training heterogeneous client architectures by incorporating a non-uniform distillation schedule and client-model mirroring on the server side., Comment: 8 Pages, 3 Figures, Appendix 4 Pages, CVPRW 2024

In noncentrosymmetric superconductors, superconducting and normal conductions can interchange based on the current flow direction. This effect is termed a superconducting diode effect (SDE), which is a focal point of recent research. The broken inversion and time reversal symmetry is believed to be the requirements of SDE but their intrinsic role has remained elusive. Here, we report strain-controlled SDEs in a layered trigonal superconductor, PbTaSe2. The SDE was found exclusively in a strained device with its absence in an unstrained device, despite that it is allowed in unstrained trigonal structure. Moreover, the zero-field or magnetic field-even (magnetic field-odd) SDE is observed when the strain and current are along armchair (zigzag) direction The results unambiguously demonstrate the intrinsic SDE under time-reversal symmetry and the critical role of strain-induced electric polarization., Comment: 35 pages, 11 figures

This paper aims to advance our understanding of how Visual Language Models (VLMs) handle privacy-sensitive information, a crucial concern as these technologies become integral to everyday life. To this end, we introduce a new benchmark PrivBench, which contains images from 8 sensitive categories such as passports, or fingerprints. We evaluate 10 state-of-the-art VLMs on this benchmark and observe a generally limited understanding of privacy, highlighting a significant area for model improvement. Based on this we introduce PrivTune, a new instruction-tuning dataset aimed at equipping VLMs with knowledge about visual privacy. By tuning two pretrained VLMs, TinyLLaVa and MiniGPT-v2, on this small dataset, we achieve strong gains in their ability to recognize sensitive content, outperforming even GPT4-V. At the same time, we show that privacy-tuning only minimally affects the VLMs performance on standard benchmarks such as VQA. Overall, this paper lays out a crucial challenge for making VLMs effective in handling real-world data safely and provides a simple recipe that takes the first step towards building privacy-aware VLMs., Comment: preprint

We introduce Bitune, a method that improves instruction-tuning of pretrained decoder-only large language models, leading to consistent gains on downstream tasks. Bitune applies both causal and bidirectional attention to the prompt, to obtain a better representation of the query or instruction. We realize this by introducing two sets of parameters, for which we apply parameter-efficient finetuning techniques. These causal and bidirectional features are then combined into a weighted average with trainable coefficients, which is subsequently used to generate new tokens. We demonstrate significant improvements in zero-shot performance on commonsense reasoning, arithmetic, and language understanding tasks, while extensive ablation studies validate the role of each component and demonstrate the method's agnosticism to different PEFT techniques.

Self-Supervised Learning (SSL) is a valuable and robust training methodology for contemporary Deep Neural Networks (DNNs), enabling unsupervised pretraining on a 'pretext task' that does not require ground-truth labels/annotation. This allows efficient representation learning from massive amounts of unlabeled training data, which in turn leads to increased accuracy in a 'downstream task' by exploiting supervised transfer learning. Despite the relatively straightforward conceptualization and applicability of SSL, it is not always feasible to collect and/or to utilize very large pretraining datasets, especially when it comes to real-world application settings. In particular, in cases of specialized and domain-specific application scenarios, it may not be achievable or practical to assemble a relevant image pretraining dataset in the order of millions of instances or it could be computationally infeasible to pretrain at this scale, e.g., due to unavailability of sufficient computational resources that SSL methods typically require to produce improved visual analysis results. This situation motivates an investigation on the effectiveness of common SSL pretext tasks, when the pretraining dataset is of relatively limited/constrained size. This work briefly introduces the main families of modern visual SSL methods and, subsequently, conducts a thorough comparative experimental evaluation in the low-data regime, targeting to identify: a) what is learnt via low-data SSL pretraining, and b) how do different SSL categories behave in such training scenarios. Interestingly, for domain-specific downstream tasks, in-domain low-data SSL pretraining outperforms the common approach of large-scale pretraining on general datasets., Comment: Article published in Elsevier's Neurocomputing journal: https://www.sciencedirect.com/science/article/pii/S0925231224019702

The COVID19 pandemic had enormous economic and societal consequences. Contact tracing is an effective way to reduce infection rates by detecting potential virus carriers early. However, this was not generally adopted in the recent pandemic, and privacy concerns are cited as the most important reason. We substantially improve the privacy guarantees of the current state of the art in decentralized contact tracing. Whereas previous work was based on statistical inference only, we augment the inference with a learned neural network and ensure that this neural augmentation satisfies differential privacy. In a simulator for COVID19, even at epsilon=1 per message, this can significantly improve the detection of potentially infected individuals and, as a result of targeted testing, reduce infection rates. This work marks an important first step in integrating deep learning into contact tracing while maintaining essential privacy guarantees., Comment: Privacy Regulation and Protection in Machine Learning Workshop at ICLR 2024

Last couple of years have witnessed a tremendous progress in self-supervised learning (SSL), the success of which can be attributed to the introduction of useful inductive biases in the learning process to learn meaningful visual representations while avoiding collapse. These inductive biases and constraints manifest themselves in the form of different optimization formulations in the SSL techniques, e.g. by utilizing negative examples in a contrastive formulation, or exponential moving average and predictor in BYOL and SimSiam. In this paper, we provide a framework to explain the stability mechanism of these different SSL techniques: i) we discuss the working mechanism of contrastive techniques like SimCLR, non-contrastive techniques like BYOL, SWAV, SimSiam, Barlow Twins, and DINO; ii) we provide an argument that despite different formulations these methods implicitly optimize a similar objective function, i.e. minimizing the magnitude of the expected representation over all data samples, or the mean of the data distribution, while maximizing the magnitude of the expected representation of individual samples over different data augmentations; iii) we provide mathematical and empirical evidence to support our framework. We formulate different hypotheses and test them using the Imagenet100 dataset., Comment: Additional visualizations (.gif): https://github.com/abskjha/CenterVectorSSL

Vision-Language Models (VLMs), such as Flamingo and GPT-4V, have shown immense potential by integrating large language models with vision systems. Nevertheless, these models face challenges in the fundamental computer vision task of object localisation, due to their training on multimodal data containing mostly captions without explicit spatial grounding. While it is possible to construct custom, supervised training pipelines with bounding box annotations that integrate with VLMs, these result in specialized and hard-to-scale models. In this paper, we aim to explore the limits of caption-based VLMs and instead propose to tackle the challenge in a simpler manner by i) keeping the weights of a caption-based VLM frozen and ii) not using any supervised detection data. To this end, we introduce an input-agnostic Positional Insert (PIN), a learnable spatial prompt, containing a minimal set of parameters that are slid inside the frozen VLM, unlocking object localisation capabilities. Our PIN module is trained with a simple next-token prediction task on synthetic data without requiring the introduction of new output heads. Our experiments demonstrate strong zero-shot localisation performances on a variety of images, including Pascal VOC, COCO, LVIS, and diverse images like paintings or cartoons.

Diffusion-based video editing have reached impressive quality and can transform either the global style, local structure, and attributes of given video inputs, following textual edit prompts. However, such solutions typically incur heavy memory and computational costs to generate temporally-coherent frames, either in the form of diffusion inversion and/or cross-frame attention. In this paper, we conduct an analysis of such inefficiencies, and suggest simple yet effective modifications that allow significant speed-ups whilst maintaining quality. Moreover, we introduce Object-Centric Diffusion, to fix generation artifacts and further reduce latency by allocating more computations towards foreground edited regions, arguably more important for perceptual quality. We achieve this by two novel proposals: i) Object-Centric Sampling, decoupling the diffusion steps spent on salient or background regions and spending most on the former, and ii) Object-Centric Token Merging, which reduces cost of cross-frame attention by fusing redundant tokens in unimportant background regions. Both techniques are readily applicable to a given video editing model without retraining, and can drastically reduce its memory and computational cost. We evaluate our proposals on inversion-based and control-signal-based editing pipelines, and show a latency reduction up to 10x for a comparable synthesis quality. Project page: qualcomm-ai-research.github.io/object-centric-diffusion., Comment: ECCV24

State-of-the-art language models are becoming increasingly large in an effort to achieve the highest performance on large corpora of available textual data. However, the sheer size of the Transformer architectures makes it difficult to deploy models within computational, environmental or device-specific constraints. We explore data-driven compression of existing pretrained models as an alternative to training smaller models from scratch. To do so, we scale Kronecker-factored curvature approximations of the target loss landscape to large language models. In doing so, we can compute both the dynamic allocation of structures that can be removed as well as updates of remaining weights that account for the removal. We provide a general framework for unstructured, semi-structured and structured pruning and improve upon weight updates to capture more correlations between weights, while remaining computationally efficient. Experimentally, our method can prune rows and columns from a range of OPT models and Llamav2-7B by 20%-30%, with a negligible loss in performance, and achieve state-of-the-art results in unstructured and semi-structured pruning of large language models.

The pandemic in 2020 and 2021 had enormous economic and societal consequences, and studies show that contact tracing algorithms can be key in the early containment of the virus. While large strides have been made towards more effective contact tracing algorithms, we argue that privacy concerns currently hold deployment back. The essence of a contact tracing algorithm constitutes the communication of a risk score. Yet, it is precisely the communication and release of this score to a user that an adversary can leverage to gauge the private health status of an individual. We pinpoint a realistic attack scenario and propose a contact tracing algorithm with differential privacy guarantees against this attack. The algorithm is tested on the two most widely used agent-based COVID19 simulators and demonstrates superior performance in a wide range of settings. Especially for realistic test scenarios and while releasing each risk score with epsilon=1 differential privacy, we achieve a two to ten-fold reduction in the infection rate of the virus. To the best of our knowledge, this presents the first contact tracing algorithm with differential privacy guarantees when revealing risk scores for COVID19., Comment: Accepted to The 38th Annual AAAI Conference on Artificial Intelligence (AAAI 2024)

Human motion synthesis is a fundamental task in computer animation. Recent methods based on diffusion models or GPT structure demonstrate commendable performance but exhibit drawbacks in terms of slow sampling speeds and error accumulation. In this paper, we propose \emph{Motion Flow Matching}, a novel generative model designed for human motion generation featuring efficient sampling and effectiveness in motion editing applications. Our method reduces the sampling complexity from thousand steps in previous diffusion models to just ten steps, while achieving comparable performance in text-to-motion and action-to-motion generation benchmarks. Noticeably, our approach establishes a new state-of-the-art Fr\'echet Inception Distance on the KIT-ML dataset. What is more, we tailor a straightforward motion editing paradigm named \emph{sampling trajectory rewriting} leveraging the ODE-style generative models and apply it to various editing scenarios including motion prediction, motion in-between prediction, motion interpolation, and upper-body editing. Our code will be released., Comment: WIP

Novel View Synthesis (NVS), which tries to produce a realistic image at the target view given source view images and their corresponding poses, is a fundamental problem in 3D Vision. As this task is heavily under-constrained, some recent work, like Zero123, tries to solve this problem with generative modeling, specifically using pre-trained diffusion models. Although this strategy generalizes well to new scenes, compared to neural radiance field-based methods, it offers low levels of flexibility. For example, it can only accept a single-view image as input, despite realistic applications often offering multiple input images. This is because the source-view images and corresponding poses are processed separately and injected into the model at different stages. Thus it is not trivial to generalize the model into multi-view source images, once they are available. To solve this issue, we try to process each pose image pair separately and then fuse them as a unified visual representation which will be injected into the model to guide image synthesis at the target-views. However, inconsistency and computation costs increase as the number of input source-view images increases. To solve these issues, the Multi-view Cross Former module is proposed which maps variable-length input data to fix-size output data. A two-stage training strategy is introduced to further improve the efficiency during training time. Qualitative and quantitative evaluation over multiple datasets demonstrates the effectiveness of the proposed method against previous approaches. The code will be released according to the acceptance., Comment: paper and supplementary material

Guidance serves as a key concept in diffusion models, yet its effectiveness is often limited by the need for extra data annotation or classifier pretraining. That is why guidance was harnessed from self-supervised learning backbones, like DINO. However, recent studies have revealed that the feature representation derived from diffusion model itself is discriminative for numerous downstream tasks as well, which prompts us to propose a framework to extract guidance from, and specifically for, diffusion models. Our research has yielded several significant contributions. Firstly, the guidance signals from diffusion models are on par with those from class-conditioned diffusion models. Secondly, feature regularization, when based on the Sinkhorn-Knopp algorithm, can further enhance feature discriminability in comparison to unconditional diffusion models. Thirdly, we have constructed an online training approach that can concurrently derive guidance from diffusion models for diffusion models. Lastly, we have extended the application of diffusion models along the constant velocity path of ODE to achieve a more favorable balance between sampling steps and fidelity. The performance of our methods has been outstanding, outperforming related baseline comparisons in large-resolution datasets, such as ImageNet256, ImageNet256-100 and LSUN-Churches. Our code will be released., Comment: Work In Progress

Self-supervised learning has unlocked the potential of scaling up pretraining to billions of images, since annotation is unnecessary. But are we making the best use of data? How more economical can we be? In this work, we attempt to answer this question by making two contributions. First, we investigate first-person videos and introduce a "Walking Tours" dataset. These videos are high-resolution, hours-long, captured in a single uninterrupted take, depicting a large number of objects and actions with natural scene transitions. They are unlabeled and uncurated, thus realistic for self-supervision and comparable with human learning. Second, we introduce a novel self-supervised image pretraining method tailored for learning from continuous videos. Existing methods typically adapt image-based pretraining approaches to incorporate more frames. Instead, we advocate a "tracking to learn to recognize" approach. Our method called DoRA, leads to attention maps that Discover and tRAck objects over time in an end-to-end manner, using transformer cross-attention. We derive multiple views from the tracks and use them in a classical self-supervised distillation loss. Using our novel approach, a single Walking Tours video remarkably becomes a strong competitor to ImageNet for several image and video downstream tasks., Comment: Accepted to ICLR 2024 (Best paper honorable mention). Project Page: https://shashankvkt.github.io/dora

We present Self-Context Adaptation (SeCAt), a self-supervised approach that unlocks few-shot abilities for open-ended classification with small visual language models. Our approach imitates image captions in a self-supervised way based on clustering a large pool of images followed by assigning semantically-unrelated names to clusters. By doing so, we construct a training signal consisting of interleaved sequences of image and pseudocaption pairs and a query image, which we denote as the 'self-context' sequence. Based on this signal the model is trained to produce the right pseudo-caption. We demonstrate the performance and flexibility of SeCAt on several multimodal few-shot datasets, spanning various granularities. By using models with approximately 1B parameters we outperform the few-shot abilities of much larger models, such as Frozen and FROMAGe. SeCAt opens new possibilities for research and applications in open-ended few-shot learning that otherwise requires access to large or proprietary models.

Spatially dense self-supervised learning is a rapidly growing problem domain with promising applications for unsupervised segmentation and pretraining for dense downstream tasks. Despite the abundance of temporal data in the form of videos, this information-rich source has been largely overlooked. Our paper aims to address this gap by proposing a novel approach that incorporates temporal consistency in dense self-supervised learning. While methods designed solely for images face difficulties in achieving even the same performance on videos, our method improves not only the representation quality for videos-but also images. Our approach, which we call time-tuning, starts from image-pretrained models and fine-tunes them with a novel self-supervised temporal-alignment clustering loss on unlabeled videos. This effectively facilitates the transfer of high-level information from videos to image representations. Time-tuning improves the state-of-the-art by 8-10% for unsupervised semantic segmentation on videos and matches it for images. We believe this method paves the way for further self-supervised scaling by leveraging the abundant availability of videos. The implementation can be found here : https://github.com/SMSD75/Timetuning

In the past years, the application of neural networks as an alternative to classical numerical methods to solve Partial Differential Equations has emerged as a potential paradigm shift in this century-old mathematical field. However, in terms of practical applicability, computational cost remains a substantial bottleneck. Classical approaches try to mitigate this challenge by limiting the spatial resolution on which the PDEs are defined. For neural PDE solvers, we can do better: Here, we investigate the potential of state-of-the-art quantization methods on reducing computational costs. We show that quantizing the network weights and activations can successfully lower the computational cost of inference while maintaining performance. Our results on four standard PDE datasets and three network architectures show that quantization-aware training works across settings and three orders of FLOPs magnitudes. Finally, we empirically demonstrate that Pareto-optimality of computational cost vs performance is almost always achieved only by incorporating quantization., Comment: Accepted at the ICCV 2023 Workshop on Resource Efficient Deep Learning for Computer Vision

While recent supervised methods for reference-based object counting continue to improve the performance on benchmark datasets, they have to rely on small datasets due to the cost associated with manually annotating dozens of objects in images. We propose UnCounTR, a model that can learn this task without requiring any manual annotations. To this end, we construct "Self-Collages", images with various pasted objects as training samples, that provide a rich learning signal covering arbitrary object types and counts. Our method builds on existing unsupervised representations and segmentation techniques to successfully demonstrate for the first time the ability of reference-based counting without manual supervision. Our experiments show that our method not only outperforms simple baselines and generic models such as FasterRCNN and DETR, but also matches the performance of supervised counting models in some domains., Comment: Accepted at CVPR'24. Code available at https://github.com/lukasknobel/SelfCollages

Identifying the causal variables of an environment and how to intervene on them is of core value in applications such as robotics and embodied AI. While an agent can commonly interact with the environment and may implicitly perturb the behavior of some of these causal variables, often the targets it affects remain unknown. In this paper, we show that causal variables can still be identified for many common setups, e.g., additive Gaussian noise models, if the agent's interactions with a causal variable can be described by an unknown binary variable. This happens when each causal variable has two different mechanisms, e.g., an observational and an interventional one. Using this identifiability result, we propose BISCUIT, a method for simultaneously learning causal variables and their corresponding binary interaction variables. On three robotic-inspired datasets, BISCUIT accurately identifies causal variables and can even be scaled to complex, realistic environments for embodied AI., Comment: Published in: Uncertainty in Artificial Intelligence (UAI 2023). Project page: https://phlippe.github.io/BISCUIT/

In this paper we address the task of finding representative subsets of points in a 3D point cloud by means of a point-wise ordering. Only a few works have tried to address this challenging vision problem, all with the help of hard to obtain point and cloud labels. Different from these works, we introduce the task of point-wise ordering in 3D point clouds through self-supervision, which we call self-ordering. We further contribute the first end-to-end trainable network that learns a point-wise ordering in a self-supervised fashion. It utilizes a novel differentiable point scoring-sorting strategy and it constructs an hierarchical contrastive scheme to obtain self-supervision signals. We extensively ablate the method and show its scalability and superior performance even compared to supervised ordering methods on multiple datasets and tasks including zero-shot ordering of point clouds from unseen categories.

The current dominant paradigm when building a machine learning model is to iterate over a dataset over and over until convergence. Such an approach is non-incremental, as it assumes access to all images of all categories at once. However, for many applications, non-incremental learning is unrealistic. To that end, researchers study incremental learning, where a learner is required to adapt to an incoming stream of data with a varying distribution while preventing forgetting of past knowledge. Significant progress has been made, however, the vast majority of works focus on the fully supervised setting, making these algorithms label-hungry thus limiting their real-life deployment. To that end, in this paper, we make the first attempt to survey recently growing interest in label-efficient incremental learning. We identify three subdivisions, namely semi-, few-shot- and self-supervised learning to reduce labeling efforts. Finally, we identify novel directions that can further enhance label-efficiency and improve incremental learning scalability. Project website: https://github.com/kilickaya/label-efficient-il.

This work aims to improve the efficiency of vision transformers (ViT). While ViTs use computationally expensive self-attention operations in every layer, we identify that these operations are highly correlated across layers -- a key redundancy that causes unnecessary computations. Based on this observation, we propose SkipAt, a method to reuse self-attention computation from preceding layers to approximate attention at one or more subsequent layers. To ensure that reusing self-attention blocks across layers does not degrade the performance, we introduce a simple parametric function, which outperforms the baseline transformer's performance while running computationally faster. We show the effectiveness of our method in image classification and self-supervised learning on ImageNet-1K, semantic segmentation on ADE20K, image denoising on SIDD, and video denoising on DAVIS. We achieve improved throughput at the same-or-higher accuracy levels in all these tasks.

Multi-modal retrieval is an important problem for many applications, such as recommendation and search. Current benchmarks and even datasets are often manually constructed and consist of mostly clean samples where all modalities are well-correlated with the content. Thus, current video-text retrieval literature largely focuses on video titles or audio transcripts, while ignoring user comments, since users often tend to discuss topics only vaguely related to the video. Despite the ubiquity of user comments online, there is currently no multi-modal representation learning datasets that includes comments. In this paper, we a) introduce a new dataset of videos, titles and comments; b) present an attention-based mechanism that allows the model to learn from sometimes irrelevant data such as comments; c) show that by using comments, our method is able to learn better, more contextualised, representations for image, video and audio representations. Project page: https://unitaryai.github.io/vtc-paper., Comment: Accepted paper at the European Conference on Computer Vision (ECCV) 2022

With the introduction of the transformer architecture in computer vision, increasing model scale has been demonstrated as a clear path to achieving performance and robustness gains. However, with model parameter counts reaching the billions, classical finetuning approaches are becoming increasingly limiting and even unfeasible when models become hosted as inference APIs, as in NLP. Visual input-prompt learning, an adaptation technique in which additional inputs in visual (RGB) space are learned, has emerged as a potential solution for adapting frozen and cloud-hosted models, requiring neither access to the forward pass, nor post-processing. Yet so far, these constraints have deteriorated adaptation performances significantly. To this end, we propose the Prompt Generation Network (PGN) that generates a different prompt for every data point, which is then used to adapt a frozen pretrained vision model to a target task. We show that the PGN effectively adapts pretrained models to various new datasets: It surpasses previous methods by a large margin on 12/12 datasets and even outperforms full-finetuning on 5/12, while requiring 100x fewer parameters. Lastly, we introduce the "prompt inversion" trick, with which PGNs can be efficiently trained in a latent space but deployed in RGB input space for inference., Comment: Accepted by BMVC2024. Codebase: https://github.com/jochemloedeman/PGN