Existing models often leverage co-occurrences between objects and their context to improve recognition accuracy. However, strongly relying on context risks a model's generalizability, especially when typical co-occurrence patterns are absent. This work focuses on addressing such contextual biases to improve the robustness of the learnt feature representations. Our goal is to accurately recognize a category in the absence of its context, without compromising on performance when it co-occurs with context. Our key idea is to decorrelate feature representations of a category from its co-occurring context. We achieve this by learning a feature subspace that explicitly represents categories occurring in the absence of context along side a joint feature subspace that represents both categories and context. Our very simple yet effective method is extensible to two multi-label tasks -- object and attribute classification. On 4 challenging datasets, we demonstrate the effectiveness of our method in reducing contextual bias.
Embodied computer vision considers perception for robots in general, unstructured environments. Of particular importance is the embodied visual exploration problem: how might a robot equipped with a camera scope out a new environment? Despite the progress thus far, many basic questions pertinent to this problem remain unanswered: (i) What does it mean for an agent to explore its environment well? (ii) Which methods work well, and under which assumptions and environmental settings? (iii) Where do current approaches fall short, and where might future work seek to improve? Seeking answers to these questions, we perform a thorough empirical study of four state-of-the-art paradigms on two photorealistic simulated 3D environments. We present a taxonomy of key exploration methods and a standard framework for benchmarking visual exploration algorithms. Our experimental results offer insights, and suggest new performance metrics and baselines for future work in visual exploration.
Moving around in the world is naturally a multisensory experience, but today's embodied agents are deaf - restricted to solely their visual perception of the environment. We introduce audio-visual navigation for complex, acoustically and visually realistic 3D environments. By both seeing and hearing, the agent must learn to navigate to an audio-based target. We develop a multi-modal deep reinforcement learning pipeline to train navigation policies end-to-end from a stream of egocentric audio-visual observations, allowing the agent to (1) discover elements of the geometry of the physical space indicated by the reverberating audio and (2) detect and follow sound-emitting targets. We further introduce audio renderings based on geometrical acoustic simulations for a set of publicly available 3D assets and instrument AI-Habitat to support the new sensor, making it possible to insert arbitrary sound sources in an array of apartment, office, and hotel environments. Our results show that audio greatly benefits embodied visual navigation in 3D spaces.
Body shape plays an important role in determining what garments will best suit a given person, yet today's clothing recommendation methods take a "one shape fits all" approach. These body-agnostic vision methods and datasets are a barrier to inclusion, ill-equipped to provide good suggestions for diverse body shapes. We introduce ViBE, a VIsual Body-aware Embedding that captures clothing's affinity with different body shapes. Given an image of a person, the proposed multi-view embedding identifies garments that will flatter her specific body shape. We show how to learn the embedding from an online catalog displaying fashion models of various shapes and sizes wearing the products, and we devise a method to explain the algorithm's suggestions for well-fitting garments. We apply our approach to a dataset of diverse subjects, and demonstrate its strong advantages over the status quo body-agnostic recommendation, both according to automated metrics and human opinion.
In the face of the video data deluge, today's expensive clip-level classifiers are increasingly impractical. We propose a framework for efficient action recognition in untrimmed video that uses audio as a preview mechanism to eliminate both short-term and long-term visual redundancies. First, we devise an ImgAud2Vid framework that hallucinates clip-level features by distilling from lighter modalities---a single frame and its accompanying audio---reducing short-term temporal redundancy for efficient clip-level recognition. Second, building on ImgAud2Vid, we further propose ImgAud-Skimming, an attention-based long short-term memory network that iteratively selects useful moments in untrimmed videos, reducing long-term temporal redundancy for efficient video-level recognition. Extensive experiments on four action recognition datasets demonstrate that our method achieves the state-of-the-art in terms of both recognition accuracy and speed.
Standard computer vision systems assume access to intelligently captured inputs (e.g., photos from a human photographer), yet autonomously capturing good observations is a major challenge in itself. We address the problem of learning to look around: how can an agent learn to acquire informative visual observations? We propose a reinforcement learning solution, where the agent is rewarded for reducing its uncertainty about the unobserved portions of its environment. Specifically, the agent is trained to select a short sequence of glimpses after which it must infer the appearance of its full environment. To address the challenge of sparse rewards, we further introduce sidekick policy learning, which exploits the asymmetry in observability between training and test time. The proposed methods learn observation policies that not only perform the completion task for which they are trained, but also generalize to exhibit useful "look-around" behavior for a range of active perception tasks.
Learning how to interact with objects is an important step towards embodied visual intelligence, but existing techniques suffer from heavy supervision or sensing requirements. We propose an approach to learn human-object interaction "hotspots" directly from video. Rather than treat affordances as a manually supervised semantic segmentation task, our approach learns about interactions by watching videos of real human behavior and anticipating afforded actions. Given a novel image or video, our model infers a spatial hotspot map indicating how an object would be manipulated in a potential interaction, even if the object is currently at rest. Through results with both first and third person video, we show the value of grounding affordances in real human-object interactions. Not only are our weakly supervised hotspots competitive with strongly supervised affordance methods, but they can also anticipate object interaction for novel object categories. Project page: http://vision.cs.utexas.edu/projects/interaction-hotspots/
Foreground object segmentation is a critical step for many image analysis tasks. While automated methods can produce high-quality results, their failures disappoint users in need of practical solutions. We propose a resource allocation framework for predicting how best to allocate a fixed budget of human annotation effort in order to collect higher quality segmentations for a given batch of images and automated methods. The framework is based on a prediction module that estimates the quality of given algorithm-drawn segmentations. We demonstrate the value of the framework for two novel tasks related to predicting how to distribute annotation efforts between algorithms and humans. Specifically, we develop two systems that automatically decide, for a batch of images, when to recruit humans versus computers to create 1) coarse segmentations required to initialize segmentation tools and 2) final, fine-grained segmentations. Experiments demonstrate the advantage of relying on a mix of human and computer efforts over relying on either resource alone for segmenting objects in images coming from three diverse modalities (visible, phase contrast microscopy, and fluorescence microscopy).
The body pose of a person wearing a camera is of great interest for applications in augmented reality, healthcare, and robotics, yet much of the person's body is out of view for a typical wearable camera. We propose a learning-based approach to estimate the camera wearer's 3D body pose from egocentric video sequences. Our key insight is to leverage interactions with another person---whose body pose we can directly observe---as a signal inherently linked to the body pose of the first-person subject. We show that since interactions between individuals often induce a well-ordered series of back-and-forth responses, it is possible to learn a temporal model of the interlinked poses even though one party is largely out of view. We demonstrate our idea on a variety of domains with dyadic interaction and show the substantial impact on egocentric body pose estimation, which improves the state of the art. Video results are available at http://vision.cs.utexas.edu/projects/you2me/