Search

In this paper, we show that adversarial training time attacks by a few pixel modifications can cause undesirable overfitting in neural networks for both discriminative and generative models. We propose an evolutionary algorithm to search for an optimal pixel attack using a novel cost function inspired by domain adaptation literature to design our training time attack. The proposed cost function explicitly maximizes the generalization gap and domain divergence between clean and corrupted images. Empirical evaluations demonstrate that our adversarial training attack can achieve significantly low testing accuracy (with high training accuracy) on multiple datasets by just perturbing a single pixel in the training images. Even under the use of popular regularization techniques, we identify a significant performance drop compared to clean data training. Our attack is more successful than previous pixel-based training time attacks on state-of-the-art Convolutional Neural Networks (CNNs) architectures, as evidenced by significantly lower testing accuracy. Interestingly, we find that the choice of optimization plays an essential role in robustness against our attack. We empirically observe that Stochastic Gradient Descent (SGD) is resilient to the proposed adversarial training attack, different from adaptive optimization techniques such as the popular Adam optimizer. We identify that such vulnerabilities are caused due to over-reliance on the cross-entropy (CE) loss on highly predictive features. Therefore, we propose a robust loss function that maximizes the mutual information between latent features and input images, in addition to optimizing the CE loss. Finally, we show that the discriminator in Generative Adversarial Networks (GANs) can also be attacked by our proposed training time attack resulting in poor generative performance. Our paper is one of the first works to design attacks for generative models.

Planetary surface images are collected by sophisticated imaging devices onboard the orbiting spacecraft. Although these images enable scientists to discover and visualize the unknown, they often suffer from the `no-data' region because the data could not be acquired by the onboard instrument due to the limitation in operation time of the instrument and satellite orbiter control. This greatly reduces the usability of the captured data for scientific purposes. To alleviate this problem, in this article, we propose a machine learning-based `no-data' region prediction algorithm. Specifically, we leverage a deep convolutional neural network (CNN) based image inpainting algorithm to predict such unphotographed pixels in a context-aware fashion using adversarial learning on planetary images. The benefit of using our proposed method is to augment features in the unphotographed regions leading to better downstream tasks such as interesting landmark classification. We use the Moon and Mars orbital images captured by the JAXA's Kaguya mission and NASA's Mars Reconnaissance Orbiter (MRO) for experimental purposes and demonstrate that our method can fill in the unphotographed regions on the Moon and Mars images with good visual and perceptual quality as measured by improved PSNR and SSIM scores. Additionally, our image inpainting algorithm helps in improved feature learning for CNN-based landmark classification as evidenced by an improved F1-score of 0.88 compared to 0.83 on the original Mars dataset.COMP: Please replace colons appearing after figure numbers and table numbers with period in all figure and table captions.

Text-based games (TBGs) have become a popular proving ground for the demonstration of learning-based agents that make decisions in quasi real-world settings. The crux of the problem for a reinforcement learning agent in such TBGs is identifying the objects in the world, and those objects' relations with that world. While the recent use of text-based resources for increasing an agent's knowledge and improving its generalization have shown promise, we posit in this paper that there is much yet to be learned from visual representations of these same worlds. Specifically, we propose to retrieve images that represent specific instances of text observations from the world and train our agents on such images. This improves the agent's overall understanding of the game scene and objects' relationships to the world around them, and the variety of visual representations on offer allow the agent to generate a better generalization of a relationship. We show that incorporating such images improves the performance of agents in various TBG settings.

Existing methods for visual anomaly detection predominantly rely on global level pixel comparisons for anomaly score computation without emphasizing on unique local features. However, images from real-world applications are susceptible to unwanted noise and distractions, that might jeopardize the robustness of such anomaly score. To alleviate this problem, we propose a self-supervised masking method that specifically focuses on discriminative parts of images to enable robust anomaly detection. Our experiments reveal that discriminator’s class activation map in adversarial training evolves in three stages and finally fixates on the foreground location in the images. Using this property of the activation map, we construct a mask that suppresses spurious signals from the background thus enabling robust anomaly detection by focusing on local discriminative attributes. Additionally, our method can further improve the accuracy by learning a semi-supervised discriminative classifier in cases where a few samples from anomaly classes are available during the training. Experimental evaluations on four different types of datasets demonstrate that our method outperforms previous state-of-the-art methods for each condition and in all domains.

Neural networks have contributed to tremendous progress in the domains of computer vision, speech processing, and other real-world applications. However, recent studies have shown that these state-of-the-art models can be easily compromised by adding small imperceptible perturbations. My thesis summary frames the problem of adversarial robustness as an equivalent problem of learning suitable features that leads to good generalization in neural networks. This is motivated from learning in humans which is not trivially fooled by such perturbations due to robust feature learning which shows good out-of-sample generalization.

We present an image inpainting technique using frequency-domain information. Prior works on image inpainting predict the missing pixels by training neural networks using only the spatial-domain information. However, these methods still struggle to reconstruct high-frequency details for real complex scenes, leading to a discrepancy in color, boundary artifacts, distorted patterns, and blurry textures. To alleviate these problems, we investigate if it is possible to obtain better performance by training the networks using frequency-domain information (discrete Fourier transform) along with the spatial-domain information. To this end, we propose a frequency-based deconvolution module that enables the network to learn the global context while selectively reconstructing the high-frequency components. We evaluate our proposed method on the publicly available datasets: celebFaces attribute (CelebA) dataset, Paris streetview, and describable textures dataset and show that our method outperforms current state-of-the-art image inpainting techniques both qualitatively and quantitatively.

We show that Reinforcement Learning (RL) methods for solving Text-Based Games (TBGs) often fail to generalize on unseen games, especially in small data regimes. To address this issue, we propose Context Relevant Episodic State Truncation (CREST) for irrelevant token removal in observation text for improved generalization. Our method first trains a base model using Q-learning, which typically overfits the training games. The base model's action token distribution is used to perform observation pruning that removes irrelevant tokens. A second bootstrapped model is then retrained on the pruned observation text. Our bootstrapped agent shows improved generalization in solving unseen TextWorld games, using 10x-20x fewer training games compared to previous state-of-the-art methods despite requiring less number of training episodes., Comment: Accepted to EMNLP 2020

Image-based sports analytics enable automatic retrieval of key events in a game to speed up the analytics process for human experts. However, most existing methods focus on structured television broadcast video datasets with a straight and fixed camera having minimum variability in the capturing pose. In this paper, we study the case of event detection in sports videos for unstructured environments with arbitrary camera angles. The transition from structured to unstructured video analysis produces multiple challenges that we address in our paper. Specifically, we identify and solve two major problems: unsupervised identification of players in an unstructured setting and generalization of the trained models to pose variations due to arbitrary shooting angles. For the first problem, we propose a temporal feature aggregation algorithm using person re-identification features to obtain high player retrieval precision by boosting a weak heuristic scoring method. Additionally, we propose a data augmentation technique, based on multi-modal image translation model, to reduce bias in the appearance of training samples. Experimental evaluations show that our proposed method improves precision for player retrieval from 0.78 to 0.86 for obliquely angled videos. Additionally, we obtain an improvement in F1 score for rally detection in table tennis videos from 0.79 in case of global frame-level features to 0.89 using our proposed player-level features. Please see the supplementary video submission at https://ibm.biz/BdzeZA., Accepted to IEEE International Symposium on Multimedia, 2019

The growing use of virtual autonomous agents in applications like games and entertainment demands better control policies for natural-looking movements and actions. Unlike the conventional approach of hard-coding motion routines, we propose a deep learning method for obtaining control policies by directly mimicking raw video demonstrations. Previous methods in this domain rely on extracting low-dimensional features from expert videos followed by a separate hand-crafted reward estimation step. We propose an imitation learning framework that reduces the dependence on hand-engineered reward functions by jointly learning the feature extraction and reward estimation steps using Generative Adversarial Networks (GANs). Our main contribution in this paper is to show that under injective mapping between low-level joint state (angles and velocities) trajectories and corresponding raw video stream, performing adversarial imitation learning on video demonstrations is equivalent to learning from the state trajectories. Experimental results show that the proposed adversarial learning method from raw videos produces a similar performance to state-of-the-art imitation learning techniques while frequently outperforming existing hand-crafted video imitation methods. Furthermore, we show that our method can learn action policies by imitating video demonstrations on YouTube with similar performance to learned agents from true reward signals. Please see the supplementary video submission at https://ibm.biz/BdzzNA., Updated the paper to match with version accepted at IEEE MMSP 2019

This paper is a contribution towards interpretability of the deep learning models in different applications of time-series. We propose a temporal attention layer that is capable of selecting the relevant information to perform various tasks, including data completion, key-frame detection and classification. The method uses the whole input sequence to calculate an attention value for each time step. This results in more focused attention values and more plausible visualisation than previous methods. We apply the proposed method to three different tasks. Experimental results show that the proposed network produces comparable results to a state of the art. In addition, the network provides better interpretability of the decision, that is, it generates more significant attention weight to related frames compared to similar techniques attempted in the past., Comment: To appear in ICPR 2018

We present a conditional generative method that maps low-dimensional embeddings of image and natural language to a common latent space hence extracting semantic relationships between them. The embedding specific to a modality is first extracted and subsequently a constrained optimization procedure is performed to project the two embedding spaces to a common manifold. Based on this, we present a method to learn the conditional probability distribution of the two embedding spaces; first, by mapping them to a shared latent space and generating back the individual embeddings from this common space. However, in order to enable independent conditional inference for separately extracting the corresponding embeddings from the common latent space representation, we deploy a proxy variable trick — wherein, the single shared latent space is replaced by two separate latent spaces. We design an objective function, such that, during training we can force these separate spaces to lie close to each other, by minimizing the Euclidean distance between their distribution functions. Experimental results demonstrate that the learned joint model can generalize to learning concepts of double MNIST digits with additional attributes of colors, thereby enabling the generation of specific colored images from the respective text data.

Crack development in concrete structures starts at the micro-crack stage and proceeds to the macro-crack stage due to repeated cyclic loading, like ongoing vehicles on bridges. Automatic detection of early stage cracks is required for both safety and economic reasons. We present an automatic crack detection method that scans a captured concrete area and provides a pixel-wise localization of both visible macro-cracks and early stage micro-cracks from video sequences. The key component in the proposed method is a spatial-temporal non-linear filtering on framewise dense 2D motion field combined with Conditional Random Fields based crack localization refinement. We evaluate our method against labeled ground truth data provided by an expert crack inspector. Experimental results show that our method can produce high accuracy automatic crack localization having F1 score improvement of 0.14-0.22 compared to conventional image based detectors. The proposed method is also shown to detect cracks at an earlier stage which enables early preventive measures for repair operations.

We present a fully convolutional network(FCN) based approach for color image restoration. FCNs have recently shown remarkable performance for high-level vision problem like semantic segmentation. In this paper, we investigate if FCN models can show promising performance for low-level problems like image restoration as well. We propose a fully convolutional model, that learns a direct end-to-end mapping between the corrupted images as input and the desired clean images as output. Our proposed method takes inspiration from domain transformation techniques but presents a data-driven task specific approach where filters for novel basis projection, task dependent coefficient alterations, and image reconstruction are represented as convolutional networks. Experimental results show that our FCN model outperforms traditional sparse coding based methods and demonstrates competitive performance compared to the state-of-the-art methods for image denoising. We further show that our proposed model can solve the difficult problem of blind image inpainting and can produce reconstructed images of impressive visual quality., Comment: Accepted at IAPR MVA 2017

This paper proposes a real-time solution to setting up a virtual trial-room for on-line portals selling apparels using a generic web camera interface to the portal. The user selects an image of an apparel from the on-line display and captures his/her own videos. The proposed method detects the pose of the user as well as various anthropomorphic features such as length and thickness of upper limbs and the dimensions of the torso. We use a background subtraction based methodology to segment out the human body from the image. The segmented human body contour is represented by a 1D curve by computing the distance of a point on the contour from the body centroid. Various extremities of body parts are found out by measuring the curvature. Using the detected feature points, we use a cloth fitting algorithm to fit the garment to the users body. The entire process is performed at 30fps, providing a realistic rendering of virtual clothing for any user

This paper proposes a realistic deformation model for pottery in which the user can interact with a rotating clay volume using a haptic tool. The deformation algorithm preserves the volume of clay to model the incompressible nature of semi-solid clay used in pottery. The interactive clay volume consists of an array of cylindrical elements stacked up vertically, providing simple and efficient collision detection and response. As a part of collision response, the force feedback consisting of both normal spring deformation force and friction force is rendered. Volume preservation is achieved by distributing the removed clay due to interactions, to the entire clay volume using a Rayleigh density function. To depict the real life pottery experience, the mechanical stability of the rotating clay volume is also included.

We present Logical Optimal Actions (LOA), an action decision architecture of reinforcement learning applications with a neuro-symbolic framework which is a combination of neural network and symbolic knowledge acquisition approach for natural language interaction games. The demonstration for LOA experiments consists of a web-based interactive platform for text-based games and visualization for acquired knowledge for improving interpretability for trained rules. This demonstration also provides a comparison module with other neuro-symbolic approaches as well as non-symbolic state-of-the-art agent models on the same text-based games. Our LOA also provides open-sourced implementation in Python for the reinforcement learning environment to facilitate an experiment for studying neuro-symbolic agents. Code: https://github.com/ibm/loa, Comment: ACL-IJCNLP 2021 (demo paper)