Danna Gurari

Nicholas J. Cooper, François G. Meyer, Michael L. Roberts et al.

We introduce a unified theoretical framework for the rigorous analysis and systematic construction of deep neural networks (DNNs). This framework addresses a gap in existing theory by explicitly modeling the structure of tensor operations -- lower level information that is often abstracted. Our framework enables two novel objectives: (1) analysis of the evolution of architectural complexity over deep learning history, and (2) automatic construction of novel architectures based on new types of tensor operations. Our study of DNNs introduced over the past 40 years reveals a connection between groundbreaking architectures and increases in different types of architectural complexity. Moreover, we identify several large classes of higher complexity architectures that have not yet been explored. We then collect a dataset of 3,000+ higher complexity architectures, which we publicly release at: https://github.com/combinatoriallabs/ArchitecturalComplexity.

Tai-Yin Chiu, Danna Gurari

Photorealistic style transfer entails transferring the style of a reference image to another image so the result seems like a plausible photo. Our work is inspired by the observation that existing models are slow due to their large sizes. We introduce PCA-based knowledge distillation to distill lightweight models and show it is motivated by theory. To our knowledge, this is the first knowledge distillation method for photorealistic style transfer. Our experiments demonstrate its versatility for use with different backbone architectures, VGG and MobileNet, across six image resolutions. Compared to existing models, our top-performing model runs at speeds 5-20x faster using at most 1\% of the parameters. Additionally, our distilled models achieve a better balance between stylization strength and content preservation than existing models. To support reproducing our method and models, we share the code at \textit{https://github.com/chiutaiyin/PCA-Knowledge-Distillation}.

Josh Myers-Dean, Yifei Fan, Brian Price et al.

Interactive segmentation entails a human marking an image to guide how a model either creates or edits a segmentation. Our work addresses limitations of existing methods: they either only support one gesture type for marking an image (e.g., either clicks or scribbles) or require knowledge of the gesture type being employed, and require specifying whether marked regions should be included versus excluded in the final segmentation. We instead propose a simplified interactive segmentation task where a user only must mark an image, where the input can be of any gesture type without specifying the gesture type. We support this new task by introducing the first interactive segmentation dataset with multiple gesture types as well as a new evaluation metric capable of holistically evaluating interactive segmentation algorithms. We then analyze numerous interactive segmentation algorithms, including ones adapted for our novel task. While we observe promising performance overall, we also highlight areas for future improvement. To facilitate further extensions of this work, we publicly share our new dataset at https://github.com/joshmyersdean/dig.

Tai-Yin Chiu, Danna Gurari

Photorealistic style transfer is the task of synthesizing a realistic-looking image when adapting the content from one image to appear in the style of another image. Modern models commonly embed a transformation that fuses features describing the content image and style image and then decodes the resulting feature into a stylized image. We introduce a general-purpose transformation that enables controlling the balance between how much content is preserved and the strength of the infused style. We offer the first experiments that demonstrate the performance of existing transformations across different style transfer models and demonstrate how our transformation performs better in its ability to simultaneously run fast, produce consistently reasonable results, and control the balance between content and style in different models. To support reproducing our method and models, we share the code at https://github.com/chiutaiyin/LS-FT.

Mina Huh, Fangyuan Xu, Yi-Hao Peng et al.

Vision language models can now generate long-form answers to questions about images - long-form visual question answers (LFVQA). We contribute VizWiz-LF, a dataset of long-form answers to visual questions posed by blind and low vision (BLV) users. VizWiz-LF contains 4.2k long-form answers to 600 visual questions, collected from human expert describers and six VQA models. We develop and annotate functional roles of sentences of LFVQA and demonstrate that long-form answers contain information beyond the question answer such as explanations and suggestions. We further conduct automatic and human evaluations with BLV and sighted people to evaluate long-form answers. BLV people perceive both human-written and generated long-form answers to be plausible, but generated answers often hallucinate incorrect visual details, especially for unanswerable visual questions (e.g., blurry or irrelevant images). To reduce hallucinations, we evaluate the ability of VQA models to abstain from answering unanswerable questions across multiple prompting strategies.

Chongyan Chen, Samreen Anjum, Danna Gurari

Visual question answering is a task of predicting the answer to a question about an image. Given that different people can provide different answers to a visual question, we aim to better understand why with answer groundings. We introduce the first dataset that visually grounds each unique answer to each visual question, which we call VQAAnswerTherapy. We then propose two novel problems of predicting whether a visual question has a single answer grounding and localizing all answer groundings. We benchmark modern algorithms for these novel problems to show where they succeed and struggle. The dataset and evaluation server can be found publicly at https://vizwiz.org/tasks-and-datasets/vqa-answer-therapy/.

Jarek Reynolds, Chandra Kanth Nagesh, Danna Gurari

Salient object detection is the task of producing a binary mask for an image that deciphers which pixels belong to the foreground object versus background. We introduce a new salient object detection dataset using images taken by people who are visually impaired who were seeking to better understand their surroundings, which we call VizWiz-SalientObject. Compared to seven existing datasets, VizWiz-SalientObject is the largest (i.e., 32,000 human-annotated images) and contains unique characteristics including a higher prevalence of text in the salient objects (i.e., in 68\% of images) and salient objects that occupy a larger ratio of the images (i.e., on average, $\sim$50\% coverage). We benchmarked seven modern salient object detection methods on our dataset and found they struggle most with images featuring salient objects that are large, have less complex boundaries, and lack text as well as for lower quality images. We invite the broader community to work on our new dataset challenge by publicly sharing the dataset at https://vizwiz.org/tasks-and-datasets/salient-object .

Yu-Yun Tseng, Alexander Bell, Danna Gurari

We introduce a few-shot localization dataset originating from photographers who authentically were trying to learn about the visual content in the images they took. It includes nearly 10,000 segmentations of 100 categories in over 4,500 images that were taken by people with visual impairments. Compared to existing few-shot object detection and instance segmentation datasets, our dataset is the first to locate holes in objects (e.g., found in 12.3\% of our segmentations), it shows objects that occupy a much larger range of sizes relative to the images, and text is over five times more common in our objects (e.g., found in 22.4\% of our segmentations). Analysis of three modern few-shot localization algorithms demonstrates that they generalize poorly to our new dataset. The algorithms commonly struggle to locate objects with holes, very small and very large objects, and objects lacking text. To encourage a larger community to work on these unsolved challenges, we publicly share our annotated few-shot dataset at https://vizwiz.org .

Chongyan Chen, Mengchen Liu, Noel Codella et al.

Visual Question Answering (VQA) entails answering questions about images. We introduce the first VQA dataset in which all contents originate from an authentic use case. Sourced from online question answering community forums, we call it VQAonline. We characterize this dataset and how it relates to eight mainstream VQA datasets. Observing that answers in our dataset tend to be much longer (i.e., a mean of 173 words) and so incompatible with standard VQA evaluation metrics, we instead utilize popular metrics for longer text evaluation for evaluating six state-of-the-art VQA models on VQAonline and report where they struggle most. Finally, we analyze which evaluation metrics align best with human judgments. To facilitate future extensions, we publicly-share the dataset at: https://vqaonline.github.io/.

Josh Myers-Dean, Jarek Reynolds, Brian Price et al.

Hierarchical segmentation entails creating segmentations at varying levels of granularity. We introduce the first hierarchical semantic segmentation dataset with subpart annotations for natural images, which we call SPIN (SubPartImageNet). We also introduce two novel evaluation metrics to evaluate how well algorithms capture spatial and semantic relationships across hierarchical levels. We benchmark modern models across three different tasks and analyze their strengths and weaknesses across objects, parts, and subparts. To facilitate community-wide progress, we publicly release our dataset at https://joshmyersdean.github.io/spin/index.html.

Yu-Yun Tseng, Tanusree Sharma, Lotus Zhang et al.

Individuals who are blind or have low vision (BLV) are at a heightened risk of sharing private information if they share photographs they have taken. To facilitate developing technologies that can help them preserve privacy, we introduce BIV-Priv-Seg, the first localization dataset originating from people with visual impairments that shows private content. It contains 1,028 images with segmentation annotations for 16 private object categories. We first characterize BIV-Priv-Seg and then evaluate modern models' performance for locating private content in the dataset. We find modern models struggle most with locating private objects that are not salient, small, and lack text as well as recognizing when private content is absent from an image. We facilitate future extensions by sharing our new dataset with the evaluation server at https://vizwiz.org/tasks-and-datasets/object-localization.

Neelima Prasad, Jarek Reynolds, Neel Karsanbhai et al.

We propose a novel task, hierarchical instance tracking, which entails tracking all instances of predefined categories of objects and parts, while maintaining their hierarchical relationships. We introduce the first benchmark dataset supporting this task, consisting of 2,765 unique entities that are tracked in 552 videos and belong to 40 categories (across objects and parts). Evaluation of seven variants of four models tailored to our novel task reveals the new dataset is challenging. Our dataset is available at https://vizwiz.org/tasks-and-datasets/hierarchical-instance-tracking/

Nicholas Cooper, Lijun Chen, Sailesh Dwivedy et al.

Knowledge distillation (KD) methods can transfer knowledge of a parameter-heavy teacher model to a light-weight student model. The status quo for feature KD methods is to utilize loss functions based on logits (i.e., pre-softmax class scores) and intermediate layer features (i.e., latent representations). Unlike previous approaches, we propose a feature KD framework for training the student's backbone using feature-based losses exclusively (i.e., without logit-based losses such as cross entropy). Leveraging recent discoveries about the geometry of latent representations, we introduce a knowledge quality metric for identifying which teacher layers provide the most effective knowledge for distillation. Experiments on three image classification datasets with four diverse student-teacher pairs, spanning convolutional neural networks and vision transformers, demonstrate our KD method achieves state-of-the-art performance, delivering top-1 accuracy boosts of up to 15% over standard approaches. We publically share our code to facilitate future work at https://github.com/Thegolfingocto/KD_wo_CE.

Mo Zhou, Josh Myers-Dean, Danna Gurari

Design prototyping involves creating mockups of products or concepts to gather feedback and iterate on ideas. While prototyping often requires specific parts of objects, such as when constructing a novel creature for a video game, existing text-to-image methods tend to only generate entire objects. To address this, we propose a novel task and method of ``part sticker generation", which entails generating an isolated part of an object on a neutral background. Experiments demonstrate our method outperforms state-of-the-art baselines with respect to realism and text alignment, while preserving object-level generation capabilities. We publicly share our code and models to encourage community-wide progress on this new task: https://partsticker.github.io.

Mengchen Liu, Chongyan Chen, Danna Gurari

While there is much excitement about the potential of large multimodal models (LMM), a comprehensive evaluation is critical to establish their true capabilities and limitations. In support of this aim, we evaluate two state-of-the-art LMMs, GPT-4V and Gemini, on a new visual question answering dataset sourced from an authentic online question answering community. We conduct fine-grained analysis by generating seven types of metadata for nearly 2,000 visual questions, such as image type and the required image processing capabilities. Our zero-shot performance analysis highlights the types of questions that are most challenging for both models, including questions related to "puzzling" topic, with "Identification" user intention, with "Sheet Music" image type, or labeled as "hard" by GPT-4.

Tanusree Sharma, Yu-Yun Tseng, Lotus Zhang et al.

Blind and low vision (BLV) individuals use Generative AI (GenAI) tools to interpret and manage visual content in their daily lives. While such tools can enhance the accessibility of visual content and so enable greater user independence, they also introduce complex challenges around visual privacy. In this paper, we investigate the current practices and future design preferences of blind and low vision individuals through an interview study with 21 participants. Our findings reveal a range of current practices with GenAI that balance privacy, efficiency, and emotional agency, with users accounting for privacy risks across six key scenarios, such as self-presentation, indoor/outdoor spatial privacy, social sharing, and handling professional content. Our findings reveal design preferences, including on-device processing, zero-retention guarantees, sensitive content redaction, privacy-aware appearance indicators, and multimodal tactile mirrored interaction methods. We conclude with actionable design recommendations to support user-centered visual privacy through GenAI, expanding the notion of privacy and responsible handling of others data.

Chongyan Chen, Yu-Yun Tseng, Zhuoheng Li et al.

No published work on visual question answering (VQA) accounts for ambiguity regarding where the content described in the question is located in the image. To fill this gap, we introduce VQ-FocusAmbiguity, the first VQA dataset that visually grounds each plausible image region a question could refer to when arriving at valid answers. We next analyze and compare our dataset to existing datasets to reveal its unique properties. Finally, we benchmark modern models for two novel tasks related to acknowledging focus ambiguity: recognizing whether a visual question has focus ambiguity and locating all plausible focus regions within the image. Results show that the dataset is challenging for modern models. To facilitate future progress on these tasks, we publicly share the dataset with an evaluation server at https://vizwiz.org/tasks-and-datasets/focus-ambiguity-in-visual-questions.

Samreen Anjum, Suyog Jain, Danna Gurari

We propose a hybrid framework for consistently producing high-quality object tracks by combining an automated object tracker with little human input. The key idea is to tailor a module for each dataset to intelligently decide when an object tracker is failing and so humans should be brought in to re-localize an object for continued tracking. Our approach leverages self-supervised learning on unlabeled videos to learn a tailored representation for a target object that is then used to actively monitor its tracked region and decide when the tracker fails. Since labeled data is not needed, our approach can be applied to novel object categories. Experiments on three datasets demonstrate our method outperforms existing approaches, especially for small, fast moving, or occluded objects.

Stuti Pandey, Josh Myers-Dean, Jarek Reynolds et al.

Lateral flow tests (LFTs) enable rapid, low-cost testing for health conditions including Covid, pregnancy, HIV, and malaria. Automated readers of LFT results can yield many benefits including empowering blind people to independently learn about their health and accelerating data entry for large-scale monitoring (e.g., for pandemics such as Covid) by using only a single photograph per LFT test. Accordingly, we explore the abilities of modern foundation vision language models (VLMs) in interpreting such tests. To enable this analysis, we first create a new labeled dataset with hierarchical segmentations of each LFT test and its nested test result window. We call this dataset LFT-Grounding. Next, we benchmark eight modern VLMs in zero-shot settings for analyzing these images. We demonstrate that current VLMs frequently fail to correctly identify the type of LFT test, interpret the test results, locate the nested result window of the LFT tests, and recognize LFT tests when they partially obfuscated. To facilitate community-wide progress towards automated LFT reading, we publicly release our dataset at https://iamstuti.github.io/lft_grounding_foundation_models/.

Maniratnam Mandal, Deepti Ghadiyaram, Danna Gurari et al.

Perception-based image analysis technologies can be used to help visually impaired people take better quality pictures by providing automated guidance, thereby empowering them to interact more confidently on social media. The photographs taken by visually impaired users often suffer from one or both of two kinds of quality issues: technical quality (distortions), and semantic quality, such as framing and aesthetic composition. Here we develop tools to help them minimize occurrences of common technical distortions, such as blur, poor exposure, and noise. We do not address the complementary problems of semantic quality, leaving that aspect for future work. The problem of assessing and providing actionable feedback on the technical quality of pictures captured by visually impaired users is hard enough, owing to the severe, commingled distortions that often occur. To advance progress on the problem of analyzing and measuring the technical quality of visually impaired user-generated content (VI-UGC), we built a very large and unique subjective image quality and distortion dataset. This new perceptual resource, which we call the LIVE-Meta VI-UGC Database, contains $40$K real-world distorted VI-UGC images and $40$K patches, on which we recorded $2.7$M human perceptual quality judgments and $2.7$M distortion labels. Using this psychometric resource we also created an automatic blind picture quality and distortion predictor that learns local-to-global spatial quality relationships, achieving state-of-the-art prediction performance on VI-UGC pictures, significantly outperforming existing picture quality models on this unique class of distorted picture data. We also created a prototype feedback system that helps to guide users to mitigate quality issues and take better quality pictures, by creating a multi-task learning framework.

Chongyan Chen, Samreen Anjum, Danna Gurari

Visual question answering is the task of answering questions about images. We introduce the VizWiz-VQA-Grounding dataset, the first dataset that visually grounds answers to visual questions asked by people with visual impairments. We analyze our dataset and compare it with five VQA-Grounding datasets to demonstrate what makes it similar and different. We then evaluate the SOTA VQA and VQA-Grounding models and demonstrate that current SOTA algorithms often fail to identify the correct visual evidence where the answer is located. These models regularly struggle when the visual evidence occupies a small fraction of the image, for images that are higher quality, as well as for visual questions that require skills in text recognition. The dataset, evaluation server, and leaderboard all can be found at the following link: https://vizwiz.org/tasks-and-datasets/answer-grounding-for-vqa/.

Josh Myers-Dean, Yinan Zhao, Brian Price et al.

Generalized few-shot semantic segmentation was introduced to move beyond only evaluating few-shot segmentation models on novel classes to include testing their ability to remember base classes. While the current state-of-the-art approach is based on meta-learning, it performs poorly and saturates in learning after observing only a few shots. We propose the first fine-tuning solution, and demonstrate that it addresses the saturation problem while achieving state-of-the-art results on two datasets, PASCAL-5i and COCO-20i. We also show that it outperforms existing methods, whether fine-tuning multiple final layers or only the final layer. Finally, we present a triplet loss regularization that shows how to redistribute the balance of performance between novel and base categories so that there is a smaller gap between them.

Tai-Yin Chiu, Danna Gurari

Photorealistic style transfer is an image editing task with the goal to modify an image to match the style of another image while ensuring the result looks like a real photograph. A limitation of existing models is that they have many parameters, which in turn prevents their use for larger image resolutions and leads to slower run-times. We introduce two mechanisms that enable our design of a more compact model that we call PhotoWCT$^2$, which preserves state-of-art stylization strength and photorealism. First, we introduce blockwise training to perform coarse-to-fine feature transformations that enable state-of-art stylization strength in a single autoencoder in place of the inefficient cascade of four autoencoders used in PhotoWCT. Second, we introduce skip connections of high-frequency residuals in order to preserve image quality when applying the sequential coarse-to-fine feature transformations. Our PhotoWCT$^2$ model requires fewer parameters (e.g., 30.3\% fewer) while supporting higher resolution images (e.g., 4K) and achieving faster stylization than existing models.

Xiaoyu Zeng, Yanan Wang, Tai-Yin Chiu et al.

The task of answering questions about images has garnered attention as a practical service for assisting populations with visual impairments as well as a visual Turing test for the artificial intelligence community. Our first aim is to identify the common vision skills needed for both scenarios. To do so, we analyze the need for four vision skills---object recognition, text recognition, color recognition, and counting---on over 27,000 visual questions from two datasets representing both scenarios. We next quantify the difficulty of these skills for both humans and computers on both datasets. Finally, we propose a novel task of predicting what vision skills are needed to answer a question about an image. Our results reveal (mis)matches between aims of real users of such services and the focus of the AI community. We conclude with a discussion about future directions for addressing the visual question answering task.

Samreen Anjum, Chi Lin, Danna Gurari

Crowdsourcing is a valuable approach for tracking objects in videos in a more scalable manner than possible with domain experts. However, existing frameworks do not produce high quality results with non-expert crowdworkers, especially for scenarios where objects split. To address this shortcoming, we introduce a crowdsourcing platform called CrowdMOT, and investigate two micro-task design decisions: (1) whether to decompose the task so that each worker is in charge of annotating all objects in a sub-segment of the video versus annotating a single object across the entire video, and (2) whether to show annotations from previous workers to the next individuals working on the task. We conduct experiments on a diversity of videos which show both familiar objects (aka - people) and unfamiliar objects (aka - cells). Our results highlight strategies for efficiently collecting higher quality annotations than observed when using strategies employed by today's state-of-art crowdsourcing system.

Yinan Zhao, Brian Price, Scott Cohen et al.

Few-shot semantic segmentation models aim to segment images after learning from only a few annotated examples. A key challenge for them is how to avoid overfitting because limited training data is available. While prior works usually limited the overall model capacity to alleviate overfitting, this hampers segmentation accuracy. We demonstrate how to increase overall model capacity to achieve improved performance, by introducing objectness, which is class-agnostic and so not prone to overfitting, for complementary use with class-specific features. Extensive experiments demonstrate the versatility of our simple approach of introducing objectness for different base architectures that rely on different data loaders and training schedules (DENet, PFENet) as well as with different backbone models (ResNet-50, ResNet-101 and HRNetV2-W48). Given only one annotated example of an unseen category, experiments show that our method outperforms state-of-art methods with respect to mIoU by at least 4.7% and 1.5% on PASCAL-5i and COCO-20i respectively.

Tai-Yin Chiu, Yinan Zhao, Danna Gurari

We introduce a new large-scale dataset that links the assessment of image quality issues to two practical vision tasks: image captioning and visual question answering. First, we identify for 39,181 images taken by people who are blind whether each is sufficient quality to recognize the content as well as what quality flaws are observed from six options. These labels serve as a critical foundation for us to make the following contributions: (1) a new problem and algorithms for deciding whether an image is insufficient quality to recognize the content and so not captionable, (2) a new problem and algorithms for deciding which of six quality flaws an image contains, (3) a new problem and algorithms for deciding whether a visual question is unanswerable due to unrecognizable content versus the content of interest being missing from the field of view, and (4) a novel application of more efficiently creating a large-scale image captioning dataset by automatically deciding whether an image is insufficient quality and so should not be captioned. We publicly-share our datasets and code to facilitate future extensions of this work: https://vizwiz.org.

Danna Gurari, Yinan Zhao, Meng Zhang et al.

While an important problem in the vision community is to design algorithms that can automatically caption images, few publicly-available datasets for algorithm development directly address the interests of real users. Observing that people who are blind have relied on (human-based) image captioning services to learn about images they take for nearly a decade, we introduce the first image captioning dataset to represent this real use case. This new dataset, which we call VizWiz-Captions, consists of over 39,000 images originating from people who are blind that are each paired with five captions. We analyze this dataset to (1) characterize the typical captions, (2) characterize the diversity of content found in the images, and (3) compare its content to that found in eight popular vision datasets. We also analyze modern image captioning algorithms to identify what makes this new dataset challenging for the vision community. We publicly-share the dataset with captioning challenge instructions at https://vizwiz.org

Nilavra Bhattacharya, Danna Gurari

We present a visualization tool to exhaustively search and browse through a set of large-scale machine learning datasets. Built on the top of the VizWiz dataset, our dataset browser tool has the potential to support and enable a variety of qualitative and quantitative research, and open new directions for visualizing and researching with multimodal information. The tool is publicly available at https://vizwiz.org/browse.

Nilavra Bhattacharya, Qing Li, Danna Gurari

Visual question answering is the task of returning the answer to a question about an image. A challenge is that different people often provide different answers to the same visual question. To our knowledge, this is the first work that aims to understand why. We propose a taxonomy of nine plausible reasons, and create two labelled datasets consisting of ~45,000 visual questions indicating which reasons led to answer differences. We then propose a novel problem of predicting directly from a visual question which reasons will cause answer differences as well as a novel algorithm for this purpose. Experiments demonstrate the advantage of our approach over several related baselines on two diverse datasets. We publicly share the datasets and code at https://vizwiz.org.

Yinan Zhao, Brian Price, Scott Cohen et al.

Many people search for foreground objects to use when editing images. While existing methods can retrieve candidates to aid in this, they are constrained to returning objects that belong to a pre-specified semantic class. We instead propose a novel problem of unconstrained foreground object (UFO) search and introduce a solution that supports efficient search by encoding the background image in the same latent space as the candidate foreground objects. A key contribution of our work is a cost-free, scalable approach for creating a large-scale training dataset with a variety of foreground objects of differing semantic categories per image location. Quantitative and human-perception experiments with two diverse datasets demonstrate the advantage of our UFO search solution over related baselines.

Danna Gurari, Yinan Zhao, Suyog Dutt Jain et al.

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).

Yinan Zhao, Brian Price, Scott Cohen et al.

Deep generative models have shown success in automatically synthesizing missing image regions using surrounding context. However, users cannot directly decide what content to synthesize with such approaches. We propose an end-to-end network for image inpainting that uses a different image to guide the synthesis of new content to fill the hole. A key challenge addressed by our approach is synthesizing new content in regions where the guidance image and the context of the original image are inconsistent. We conduct four studies that demonstrate our results yield more realistic image inpainting results over seven baselines.

Danna Gurari, Qing Li, Abigale J. Stangl et al.

The study of algorithms to automatically answer visual questions currently is motivated by visual question answering (VQA) datasets constructed in artificial VQA settings. We propose VizWiz, the first goal-oriented VQA dataset arising from a natural VQA setting. VizWiz consists of over 31,000 visual questions originating from blind people who each took a picture using a mobile phone and recorded a spoken question about it, together with 10 crowdsourced answers per visual question. VizWiz differs from the many existing VQA datasets because (1) images are captured by blind photographers and so are often poor quality, (2) questions are spoken and so are more conversational, and (3) often visual questions cannot be answered. Evaluation of modern algorithms for answering visual questions and deciding if a visual question is answerable reveals that VizWiz is a challenging dataset. We introduce this dataset to encourage a larger community to develop more generalized algorithms that can assist blind people.

Danna Gurari, Kun He, Bo Xiong et al.

We propose the ambiguity problem for the foreground object segmentation task and motivate the importance of estimating and accounting for this ambiguity when designing vision systems. Specifically, we distinguish between images which lead multiple annotators to segment different foreground objects (ambiguous) versus minor inter-annotator differences of the same object. Taking images from eight widely used datasets, we crowdsource labeling the images as "ambiguous" or "not ambiguous" to segment in order to construct a new dataset we call STATIC. Using STATIC, we develop a system that automatically predicts which images are ambiguous. Experiments demonstrate the advantage of our prediction system over existing saliency-based methods on images from vision benchmarks and images taken by blind people who are trying to recognize objects in their environment. Finally, we introduce a crowdsourcing system to achieve cost savings for collecting the diversity of all valid "ground truth" foreground object segmentations by collecting extra segmentations only when ambiguity is expected. Experiments show our system eliminates up to 47% of human effort compared to existing crowdsourcing methods with no loss in capturing the diversity of ground truths.

Danna Gurari, Kristen Grauman

Visual question answering (VQA) systems are emerging from a desire to empower users to ask any natural language question about visual content and receive a valid answer in response. However, close examination of the VQA problem reveals an unavoidable, entangled problem that multiple humans may or may not always agree on a single answer to a visual question. We train a model to automatically predict from a visual question whether a crowd would agree on a single answer. We then propose how to exploit this system in a novel application to efficiently allocate human effort to collect answers to visual questions. Specifically, we propose a crowdsourcing system that automatically solicits fewer human responses when answer agreement is expected and more human responses when answer disagreement is expected. Our system improves upon existing crowdsourcing systems, typically eliminating at least 20% of human effort with no loss to the information collected from the crowd.