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 all approaches currently are based on meta-learning, they perform poorly and saturate 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-art results on two datasets, PASCAL-$5^i$ and COCO-$20^i$. We also show 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.
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.
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.
While deep convolutional neural networks have led to great progress in image semantic segmentation, they typically require collecting a large number of densely-annotated images for training. Moreover, once trained, the model can only make predictions in a pre-defined set of categories. Therefore, few-shot image semantic segmentation has been explored to learn to segment from only a few annotated examples. In this paper, we tackle the challenging one-shot semantic segmentation problem by taking advantage of objectness. In order to capture prior knowledge of object and background, we first train an objectness segmentation module which generalizes well to unseen categories. Then we use the objectness module to predict the objects present in the query image, and train an objectness-aware few-shot segmentation model that takes advantage of both the object information and limited annotations of the unseen category to perform segmentation in the query image. Our method achieves a mIoU score of 57.9% and 22.6% given only one annotated example of an unseen category in PASCAL-5i and COCO-20i, outperforming related baselines overall.
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.
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
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.
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.
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.
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).