Vision is essential for human navigation. The World Health Organization (WHO) estimates that 43.3 million people were blind in 2020, and this number is projected to reach 61 million by 2050. Modern scene understanding models could empower these people by assisting them with navigation, obstacle avoidance and visual recognition capabilities. The research community needs high quality datasets for both training and evaluation to build these systems. While datasets for autonomous vehicles are abundant, there is a critical gap in datasets tailored for outdoor human navigation. This gap poses a major obstacle to the development of computer vision based Assistive Technologies. To overcome this obstacle, we present SANPO, a large-scale egocentric video dataset designed for dense prediction in outdoor human navigation environments. SANPO contains 701 stereo videos of 30+ seconds captured in diverse real-world outdoor environments across four geographic locations in the USA. Every frame has a high resolution depth map and 112K frames were annotated with temporally consistent dense video panoptic segmentation labels. The dataset also includes 1961 high-quality synthetic videos with pixel accurate depth and panoptic segmentation annotations to balance the noisy real world annotations with the high precision synthetic annotations. SANPO is already publicly available and is being used by mobile applications like Project Guideline to train mobile models that help low-vision users go running outdoors independently. To preserve anonymization during peer review, we will provide a link to our dataset upon acceptance.

Dense prediction tasks, such as semantic segmentation, depth estimation, and surface normal prediction, can be easily formulated as per-pixel classification (discrete outputs) or regression (continuous outputs). This per-pixel prediction paradigm has remained popular due to the prevalence of fully convolutional networks. However, on the recent frontier of segmentation task, the community has been witnessing a shift of paradigm from per-pixel prediction to cluster-prediction with the emergence of transformer architectures, particularly the mask transformers, which directly predicts a label for a mask instead of a pixel. Despite this shift, methods based on the per-pixel prediction paradigm still dominate the benchmarks on the other dense prediction tasks that require continuous outputs, such as depth estimation and surface normal prediction. Motivated by the success of DORN and AdaBins in depth estimation, achieved by discretizing the continuous output space, we propose to generalize the cluster-prediction based method to general dense prediction tasks. This allows us to unify dense prediction tasks with the mask transformer framework. Remarkably, the resulting model PolyMaX demonstrates state-of-the-art performance on three benchmarks of NYUD-v2 dataset. We hope our simple yet effective design can inspire more research on exploiting mask transformers for more dense prediction tasks. Code and model will be made available1.

Recent self-supervised representation learning techniques have largely closed the gap between supervised and unsupervised learning on ImageNet classification. While the particulars of pretraining on ImageNet are now relatively well understood, the field still lacks widely accepted best practices for replicating this success on other datasets. As a first step in this direction, we study contrastive self-supervised learning on four diverse large-scale datasets. By looking through the lenses of data quantity, data domain, data quality, and task granularity, we provide new insights into the necessary conditions for successful self-supervised learning. Our key findings include observations such as: (i) the benefit of additional pretraining data beyond 500k images is modest, (ii) adding pretraining images from another domain does not lead to more general representations, (iii) corrupted pretraining images have a disparate impact on supervised and self-supervised pretraining, and (iv) contrastive learning lags far behind supervised learning on finegrained visual classification tasks.

Recent progress in self-supervised learning has resulted in models that are capable of extracting rich representations from image collections without requiring any explicit label supervision. However, to date the vast majority of these approaches have restricted themselves to training on standard benchmark datasets such as ImageNet. We argue that fine-grained visual categorization problems, such as plant and animal species classification, provide an informative testbed for self-supervised learning. In order to facilitate progress in this area we present two new natural world visual classification datasets, iNat2021 and NeWT. The former consists of 2.7M images from 10k different species up-loaded by users of the citizen science application iNaturalist. We designed the latter, NeWT, in collaboration with domain experts with the aim of benchmarking the performance of representation learning algorithms on a suite of challenging natural world binary classification tasks that go beyond standard species classification. These two new datasets allow us to explore questions related to large-scale representation and transfer learning in the context of fine-grained categories. We provide a comprehensive analysis of feature extractors trained with and without supervision on ImageNet and iNat2021, shedding light on the strengths and weaknesses of different learned features across a diverse set of tasks. We find that features produced by standard supervised methods still outperform those produced by self-supervised approaches such as SimCLR. However, improved self-supervised learning methods are constantly being released and the iNat2021 and NeWT datasets are a valuable resource for tracking their progress.

As any savvy online shopper knows, second-hand peer-to-peer marketplaces are filled with images of mixed quality. How does image quality impact marketplace outcomes, and can quality be automatically predicted? In this work, we conducted a large-scale study on the quality of user-generated images in peer-to-peer marketplaces. By gathering a dataset of common second-hand products (≈75,000 images) and annotating a subset with human-labeled quality judgments, we were able to model and predict image quality with decent accuracy (≈87%). We then conducted two studies focused on understanding the relationship between these image quality scores and two marketplace outcomes: sales and perceived trustworthiness. We show that image quality is associated with higher likelihood that an item will be sold, though other factors such as view count were better predictors of sales. Nonetheless, we show that high quality user-generated images selected by our models outperform stock imagery in eliciting perceptions of trust from users. Our findings can inform the design of future marketplaces and guide potential sellers to take better product images.

We propose a novel measure of visual similarity for image retrieval that incorporates both structural and aesthetic (style) constraints. Our algorithm accepts a query as sketched shape, and a set of one or more contextual images specifying the desired visual aesthetic. A triplet network is used to learn a feature embedding capable of measuring style similarity independent of structure, delivering significant gains over previous networks for style discrimination. We incorporate this model within a hierarchical triplet network to unify and learn a joint space from two discriminatively trained streams for style and structure. We demonstrate that this space enables, for the first time, style-constrained sketch search over a diverse domain of digital artwork comprising graphics, paintings and drawings. We also briefly explore alternative query modalities.

Computer vision systems are designed to work well within the context of everyday photography. However, artists often render the world around them in ways that do not resemble photographs. Artwork produced by people is not constrained to mimic the physical world, making it more challenging for machines to recognize.,,This work is a step toward teaching machines how to categorize images in ways that are valuable to humans. First, we collect a large-scale dataset of contemporary artwork from Behance, a website containing millions of portfolios from professional and commercial artists. We annotate Behance imagery with rich attribute labels for content, emotions, and artistic media. Furthermore, we carry out baseline experiments to show the value of this dataset for artistic style prediction, for improving the generality of existing object classifiers, and for the study of visual domain adaptation. We believe our Behance Artistic Media dataset will be a good starting point for researchers wishing to study artistic imagery and relevant problems. This dataset can be found at https://bam-dataset.org/.

Research experiences today are limited to a privileged few at select universities. Providing open access to research experiences would enable global upward mobility and increased diversity in the scientific workforce. How can we coordinate a crowd of diverse volunteers on open-ended research? How could a PI have enough visibility into each person's contributions to recommend them for further study? We present Crowd Research, a crowdsourcing technique that coordinates open-ended research through an iterative cycle of open contribution, synchronous collaboration, and peer assessment. To aid upward mobility and recognize contributions in publications, we introduce a decentralized credit system: participants allocate credits to each other, which a graph centrality algorithm translates into a collectively-created author order. Over 1,500 people from 62 countries have participated, 74% from institutions with low access to research. Over two years and three projects, this crowd has produced articles at top-tier Computer Science venues, and participants have gone on to leading graduate programs.

In this work we propose a novel interpretation of residual networks showing that they can be seen as a collection of many paths of differing length. Moreover, residual networks seem to enable very deep networks by leveraging only the short paths during training. To support this observation, we rewrite residual networks as an explicit collection of paths. Unlike traditional models, paths through residual networks vary in length. Further, a lesion study reveals that these paths show ensemble-like behavior in the sense that they do not strongly depend on each other. Finally, and most surprising, most paths are shorter than one might expect, and only the short paths are needed during training, as longer paths do not contribute any gradient. For example, most of the gradient in a residual network with 110 layers comes from paths that are only 10-34 layers deep. Our results reveal one of the key characteristics that seem to enable the training of very deep networks: Residual networks avoid the vanishing gradient problem by introducing short paths which can carry gradient throughout the extent of very deep networks.

After decades of study, automatic face detection and recognition systems are now accurate and widespread. Naturally, this means users who wish to avoid automatic recognition are becoming less able to do so. Where do we stand in this cat-and-mouse race? We currently live in a society where everyone carries a camera in their pocket. Many people willfully upload most or all of the pictures they take to social networks which invest heavily in automatic face recognition systems. In this setting, is it still possible for privacy-conscientious users to avoid automatic face detection and recognition? If so, how? Must evasion techniques be obvious to be effective, or are there still simple measures that users can use to protect themselves? In this work, we find ways to evade face detection on Facebook, a representative example of a popular social network that uses automatic face detection to enhance their service. We challenge widely-held beliefs about evading face detection: do our old techniques such as blurring the face region or wearing "privacy glasses" still work? We show that in general, state-of-the-art detectors can often find faces even if the subject wears occluding clothing or even if the uploader damages the photo to prevent faces from being detected.

This paper presents our work on "SNaCK," a low-dimensional concept embedding algorithm that combines human expertise with automatic machine similarity kernels. Both parts are complimentary: human insight can capture relationships that are not apparent from the object's visual similarity and the machine can help relieve the human from having to exhaustively specify many constraints. We show that our SNaCK embeddings are useful in several tasks: distinguishing prime and nonprime numbers on MNIST, discovering labeling mistakes in the Caltech UCSD Birds (CUB) dataset with the help of deep-learned features, creating training datasets for bird classifiers, capturing subjective human taste on a new dataset of 10,000 foods, and qualitatively exploring an unstructured set of pictographic characters. Comparisons with the state-of-the-art in these tasks show that SNaCK produces better concept embeddings that require less human supervision than the leading methods.

Similarity comparisons of the form "Is object a more similar to b than to c?" form a useful foundation in several computer vision and machine learning applications. Unfortunately, an embedding of n points is only uniquely specified by n3 triplets, making collecting every triplet an expensive task. In noticing this difficulty, other researchers investigated more intelligent triplet sampling techniques, but they do not study their effectiveness or their potential drawbacks. Although it is important to reduce the number of collected triplets to generate a good embedding, it is also important to understand how best to display a triplet collection task to the user to better respect the worker's human constraints. In this work, we explore an alternative method for collecting triplets and analyze its financial cost, collection speed, and worker happiness as a function of the final embedding quality. We propose best practices for creating cost effective human intelligence tasks for collecting triplets. We show that rather than changing the sampling algorithm, simple changes to the crowdsourcing UI can drastically decrease the cost of collecting similarity comparisons. Finally, we provide a food similarity dataset as well as the labels collected from crowd workers.

When implementing real-world computer vision systems, researchers can use mid-level representations as a tool to adjust the trade-off between accuracy and efficiency. Unfortunately, existing mid-level representations that improve accuracy tend to decrease efficiency, or are specifically tailored to work well within one pipeline or vision problem at the exclusion of others. We introduce a novel, efficient mid-level representation that improves classification efficiency without sacrificing accuracy. Our Exemplar Codes are based on linear classifiers and probability normalization from extreme value theory. We apply Exemplar Codes to two problems: facial attribute extraction and tattoo classification. In these settings, our Exemplar Codes are competitive with the state of the art and offer efficiency benefits, making it possible to achieve high accuracy even on commodity hardware with a low computational budget.

The outreach of computer vision to non-traditional areas has enormous potential to enable new ways of solving real world problems. One such problem is how to incorporate technology in the effort to protect endangered and threatened species in the wild. This paper presents a snapshot of our interdisciplinary team's ongoing work in the Mojave Desert to build vision tools for field biologists to study the currently threatened Desert Tortoise and Mohave Ground Squirrel. Animal population studies in natural habitats present new recognition challenges for computer vision, where open set testing and access to just limited computing resources lead us to algorithms that diverge from common practices. We introduce a novel algorithm for animal classification that addresses the open set nature of this problem and is suitable for implementation on a smartphone. Further, we look at a simple model for object recognition applied to the problem of individual species identification. A thorough experimental analysis is provided for real field data collected in the Mojave desert.

As biometric authentication systems become common in everyday use, researchers are beginning to address privacy issues in biometric recognition. With the growing use of mobile devices, it is important to develop approaches that support remote mobile verification. This paper outlines the need for a mobile/remote SVM-based authentication system that does not compromise the privacy of the subject being recognized. We discuss limitations of earlier privacy-preserving authentication systems and present necessary privacy and security requirements that make a system attractive from both the server's security point of view and from the client's privacy-centric point of view. We then present a novel protocol we call “Vaulted Verification” that allows a server to remotely authenticate a client's biometric in a privacy preserving way. We conclude with a small evaluation of performance, discussion of security implications, and ideas for future work.

Face and eye detection algorithms are deployed in a wide variety of applications. Unfortunately, there has been no quantitative comparison of how these detectors perform under difficult circumstances. We created a dataset of low light and long distance images which possess some of the problems encountered by face and eye detectors solving real world problems. The dataset we created is composed of reimaged images (photohead) and semi-synthetic heads imaged under varying conditions of low light, atmospheric blur, and distances of 3m, 50m, 80m, and 200m. This paper analyzes the detection and localization performance of the participating face and eye algorithms compared with the Viola Jones detector and four leading commercial face detectors. Performance is characterized under the different conditions and parameterized by per-image brightness and contrast. In localization accuracy for eyes, the groups/companies focusing on long-range face detection outperform leading commercial applications.