Devi Parikh

Relative attributes

Human-nameable visual “attributes” can benefit various recognition tasks. However, existing techniques restrict these properties to categorical labels (for example, a person is ‘smiling’ or not, a scene is ‘dry’ or not), and thus fail to capture more general semantic relationships. We propose to model relative attributes. Given training data stating how object/scene categories relate according to different attributes, we learn a ranking function per attribute. The learned ranking functions predict the relative strength of each property in novel images. We then build a generative model over the joint space of attribute ranking outputs, and propose a novel form of zero-shot learning in which the supervisor relates the unseen object category to previously seen objects via attributes (for example, ‘bears are furrier than giraffes’). We further show how the proposed relative attributes enable richer textual descriptions for new images, which in practice are more precise for human interpretation. We demonstrate the approach on datasets of faces and natural scenes, and show its clear advantages over traditional binary attribute prediction for these new tasks.

VQA: Visual Question Answering

We propose the task of free-form and open-ended Visual Question Answering (VQA). Given an image and a natural language question about the image, the task is to provide an accurate natural language answer. Mirroring real-world scenarios, such as helping the visually impaired, both the questions and answers are open-ended. Visual questions selectively target different areas of an image, including background details and underlying context. As a result, a system that succeeds at VQA typically needs a more detailed understanding of the image and complex reasoning than a system producing generic image captions. Moreover, VQA is amenable to automatic evaluation, since many open-ended answers contain only a few words or a closed set of answers that can be provided in a multiple-choice format. We provide a dataset containing ~0.25M images, ~0.76M questions, and ~10M answers (www.visualqa.org), and discuss the information it provides. Numerous baselines for VQA are provided and compared with human performance.

CIDEr: Consensus-based image description evaluation

Automatically describing an image with a sentence is a long-standing challenge in computer vision and natural language processing. Due to recent progress in object detection, attribute classification, action recognition, etc., there is renewed interest in this area. However, evaluating the quality of descriptions has proven to be challenging. We propose a novel paradigm for evaluating image descriptions that uses human consensus. This paradigm consists of three main parts: a new triplet-based method of collecting human annotations to measure consensus, a new automated metric that captures consensus, and two new datasets: PASCAL-50S and ABSTRACT-50S that contain 50 sentences describing each image. Our simple metric captures human judgment of consensus better than existing metrics across sentences generated by various sources. We also evaluate five state-of-the-art image description approaches using this new protocol and provide a benchmark for future comparisons. A version of CIDEr named CIDEr-D is available as a part of MS COCO evaluation server to enable systematic evaluation and benchmarking.

iCoseg: Interactive co-segmentation with intelligent scribble guidance

This paper presents an algorithm for Interactive Co-segmentation of a foreground object from a group of related images. While previous approaches focus on unsupervised co-segmentation, we use successful ideas from the interactive object-cutout literature. We develop an algorithm that allows users to decide what foreground is, and then guide the output of the co-segmentation algorithm towards it via scribbles. Interestingly, keeping a user in the loop leads to simpler and highly parallelizable energy functions, allowing us to work with significantly more images per group. However, unlike the interactive single image counterpart, a user cannot be expected to exhaustively examine all cutouts (from tens of images) returned by the system to make corrections. Hence, we propose iCoseg, an automatic recommendation system that intelligently recommends where the user should scribble next. We introduce and make publicly available the largest co-segmentation datasetyet, the CMU-Cornell iCoseg Dataset, with 38 groups, 643 images, and pixelwise hand-annotated groundtruth. Through machine experiments and real user studies with our developed interface, we show that iCoseg can intelligently recommend regions to scribble on, and users following these recommendations can achieve good quality cutouts with significantly lower time and effort than exhaustively examining all cutouts.

Discovering localized attributes for fine-grained recognition

Attributes are visual concepts that can be detected by machines, understood by humans, and shared across categories. They are particularly useful for fine-grained domains where categories are closely related to one other (e.g. bird species recognition). In such scenarios, relevant attributes are often local (e.g. “white belly”), but the question of how to choose these local attributes remains largely unexplored. In this paper, we propose an interactive approach that discovers local attributes that are both discriminative and semantically meaningful from image datasets annotated only with fine-grained category labels and object bounding boxes. Our approach uses a latent conditional random field model to discover candidate attributes that are detectable and discriminative, and then employs a recommender system that selects attributes likely to be semantically meaningful. Human interaction is used to provide semantic names for the discovered attributes. We demonstrate our method on two challenging datasets, Caltech-UCSD Birds-200-2011 and Leeds Butterflies, and find that our discovered attributes outperform those generated by traditional approaches.

Localization and Segmentation of A 2D High Capacity Color Barcode

A 2D color barcode can hold much more information than a binary barcode. Barcodes are often intended for consumer use where using a cellphone, a consumer can take an image of a barcode on a product, and retrieve relevant information about the product. The barcode must be read using computer vision techniques. While a color barcode can hold more information, it makes this vision task in consumer scenarios unusually challenging. We present our approach to the localization and segmentation of a 2D color barcode in such challenging scenarios, along with its evaluation on a diverse collection of images of Microsofts recently launched high capacity color barcode (HCCB). We exploit the unique trait of barcode reading: the barcode decoder can give the vision algorithm feedback, and develop a progressive strategy to achieve both - high accuracy in diverse scenarios as well as computational efficiency.

Bringing Semantics into Focus Using Visual Abstraction

Relating visual information to its linguistic semantic meaning remains an open and challenging area of research. The semantic meaning of images depends on the presence of objects, their attributes and their relations to other objects. But precisely characterizing this dependence requires extracting complex visual information from an image, which is in general a difficult and yet unsolved problem. In this paper, we propose studying semantic information in abstract images created from collections of clip art. Abstract images provide several advantages. They allow for the direct study of how to infer high-level semantic information, since they remove the reliance on noisy low-level object, attribute and relation detectors, or the tedious hand-labeling of images. Importantly, abstract images also allow the ability to generate sets of semantically similar scenes. Finding analogous sets of semantically similar real images would be nearly impossible. We create 1,002 sets of 10 semantically similar abstract scenes with corresponding written descriptions. We thoroughly analyze this dataset to discover semantically important features, the relations of words to visual features and methods for measuring semantic similarity.

Knowing When to Look: Adaptive Attention via a Visual Sentinel for Image Captioning

Attention-based neural encoder-decoder frameworks have been widely adopted for image captioning. Most methods force visual attention to be active for every generated word. However, the decoder likely requires little to no visual information from the image to predict non-visual words such as the and of. Other words that may seem visual can often be predicted reliably just from the language model e.g., sign after behind a red stop or phone following talking on a cell. In this paper, we propose a novel adaptive attention model with a visual sentinel. At each time step, our model decides whether to attend to the image (and if so, to which regions) or to the visual sentinel. The model decides whether to attend to the image and where, in order to extract meaningful information for sequential word generation. We test our method on the COCO image captioning 2015 challenge dataset and Flickr30K. Our approach sets the new state-of-the-art by a significant margin.

An Ensemble-Based Incremental Learning Approach to Data Fusion

This paper introduces Learn++, an ensemble of classifiers based algorithm originally developed for incremental learning, and now adapted for information/data fusion applications. Recognizing the conceptual similarity between incremental learning and data fusion, Learn++ follows an alternative approach to data fusion, i.e., sequentially generating an ensemble of classifiers that specifically seek the most discriminating information from each data set. It was observed that Learn++ based data fusion consistently outperforms a similarly configured ensemble classifier trained on any of the individual data sources across several applications. Furthermore, even if the classifiers trained on individual data sources are fine tuned for the given problem, Learn++ can still achieve a statistically significant improvement by combining them, if the additional data sets carry complementary information. The algorithm can also identify-albeit indirectly-those data sets that do not carry such additional information. Finally, it was shown that the algorithm can consecutively learn both the supplementary novel information coming from additional data of the same source, and the complementary information coming from new data sources without requiring access to any of the previously seen data

What Makes a Photograph Memorable

When glancing at a magazine, or browsing the Internet, we are continuously exposed to photographs. Despite this overflow of visual information, humans are extremely good at remembering thousands of pictures along with some of their visual details. But not all images are equal in memory. Some stick in our minds while others are quickly forgotten. In this paper, we focus on the problem of predicting how memorable an image will be. We show that memorability is an intrinsic and stable property of an image that is shared across different viewers, and remains stable across delays. We introduce a database for which we have measured the probability that each picture will be recognized after a single view. We analyze a collection of image features, labels, and attributes that contribute to making an image memorable, and we train a predictor based on global image descriptors. We find that predicting image memorability is a task that can be addressed with current computer vision techniques. While making memorable images is a challenging task in visualization, photography, and education, this work is a first attempt to quantify this useful property of images.