Abstract

With recent advances in the field of computer vision and especially deep learning, many fully connected and convolutional neural networks have been trained to achieve state-of-the-art performance on a wide variety of tasks such as speech recognition, image classification and natural language processing. For classification tasks however, most of these deep learning models employ the softmax activation function for prediction and minimize cross-entropy loss. In contrast, we demonstrate a consistent advantage by replacing the softmax layer by a set of binary SVM classifiers organized in a tree or DAG (Directed Acyclic Graph) structure. The idea is to not treat the multiclass classification problem as a whole but to break it down into smaller binary problems where each classifier acts as an expert by focusing on differentiating between only two classes and thus improves the overall accuracy. Furthermore, by arranging the classifiers in a DAG structure, we later also show how it is possible to further improve the performance of the binary classifiers by learning more discriminative features through the same deep network. We validated the proposed methodology on two benchmark datasets, and the results corroborated our claim.

Abstract

Overhead imageries play a crucial role in many applications such as urban planning, crop yield forecasting, mapping, and policy making. Semantic segmentation could enable automatic, efficient, and large-scale understanding of overhead imageries for these applications. However, semantic segmentation of overhead imageries is a challenging task, primarily due to the large domain gap from existing research in ground imageries, unavailability of large-scale dataset with pixel-level annotations, and inherent complexity in the task. Readily available vast amount of unlabeled overhead imageries share more common structures and patterns compared to the ground imageries, therefore, its large-scale analysis could benefit from unsupervised feature learning techniques. In this work, we study various self-supervised feature learning techniques for semantic segmentation of overhead imageries. We choose image semantic inpainting as a self-supervised task [36] for our experiments due to its proximity to the semantic segmentation task. We (i) show that existing approaches are inefficient for semantic segmentation, (ii) propose architectural changes towards self-supervised learning for semantic segmentation, (iii) propose an adversarial training scheme for self-supervised learning by increasing the pretext task’s difficulty gradually and show that it leads to learning better features, and (iv) propose a unified approach for overhead scene parsing, road network extraction, and land cover estimation. Our approach improves over training from scratch by more than 10% and ImageNet pre-trained network by more than 5% mIOU.

Abstract

Semantic segmentation is a popular task in computer vision today, and deep neural network models have emerged as the popular solution to this problem in recent times. The typical loss function used to train neural networks for this task is the cross-entropy loss. However, the success of the learned models is measured using Intersection-OverUnion (IoU), which is inherently non-differentiable. This gap between performance measure and loss function results in a fall in performance, which has also been studied by few recent efforts. In this work, we propose a novel method to automatically learn a surrogate loss function that approximates the IoU loss and is better suited for good IoU performance. To the best of our knowledge, this is the first such work that attempts to learn a loss function for this purpose. The proposed loss can be directly applied over any network. We validated our method over different networks (FCN, SegNet, UNet) on the PASCAL VOC and Cityscapes datasets. Our results on this work show consistent improvement over baseline methods.

Abstract

We examine if EEG-based cognitive load (CL) estimation is generalizable across the character, spatial pattern, bar graph and pie chart-based visualizations for the n-back task. CL is estimated via two recent approaches: (a) Deep convolutional neural network [2], and (b) Proximal support vector machines [15]. Experiments reveal that CL estimation suffers across visualizations motivating the need for effective machine learning techniques to benchmark visual interface usability for a given analytic task.

Abstract

t Automatic image annotation is one of the fundamental problems in computer vision and machine learning. Given an image, here the goal is to predict a set of textual labels that describe the semantics of that image. During the last decade, a large number of image annotation techniques have been proposed that have been shown to achieve encouragingresults on various annotation datasets. However, their scope has mostly remained restricted to quantitative results on the test data, thus ignoring various key aspects related to dataset properties and evaluation metrics that inherently affect the performance to a considerable extent. In this paper, first we evaluate ten state-of-the-art (both deep-learning based as well as non-deep-learning based) approaches for image annotation using the same baseline CNN features. Then we propose new quantitative measures to examine various issues/aspects in the image annotation domain, such as dataset specific biases, per-label versus per-image evaluation criteria, and the impact of changing the number and type of predicted labels. We believe the conclusions derived in this paper through thorough empirical analyzes would be helpful in making systematic advancements in this domain.

Abstract

View-graph selection is a crucial step for accurate and efficient large-scale structure from motion (sfm). Most sfm methods remove undesirable images and pairs using several fixed heuristic criteria, and propose tailor-made solutions to achieve specific reconstruction objectives such as efficiency, accuracy, or disambiguation. In contrast to these disparate solutions, we propose an optimization based formulation that can be used to achieve these different reconstruction objectives with taskspecific cost modeling and construct a very efficient network-flow based formulation for its approximate solution. The abstraction brought on by this selection mechanism separates the challenges specific to datasets and reconstruction objectives from the standard sfm pipeline and improves its generalization. This paper mainly focuses on application of this framework with standard sfm pipeline for accurate and ghost-free reconstructions of highly ambiguous datasets. To model selection costs for this task, we introduce new disambiguation priors based on local geometry. We further demonstrate versatility of the method by using it for the general objective of accurate and efficient reconstruction of largescale Internet datasets using costs based on well-known sfm priors.

Abstract

Post-capture control of the focus position of an image is a useful photographic tool. Changing the focus of a single image involves the complex task of simultaneously estimating the radiance and the defocus radius of all scene points. We introduce RefocusGAN, a deblurthen-reblur approach to single image refocusing. We train conditional adversarial networks for deblurring and refocusing using wide-aperture images created from light-fields. By appropriately conditioning our networks with a focus measure, an in-focus image and a refocus control parameter δ, we are able to achieve generic free-form refocusing over a single image.

Abstract

Human body tracking typically requires specialized capture set-ups. Although pose tracking is available in consumer devices like Microsoft Kinect, it is restricted to stick figures visualizing body part detection. In this paper, we propose a method for full 3D human body shape and motion capture of arbitrary movements from the depth channel of a single Kinect, when the subject wears casual clothes. We do not use the RGB channel or an initialization procedure that requires the subject to move around in front of the camera. This makes our method applicable for arbitrary clothing textures and lighting environments, with minimal subject intervention. Our method consists of 3D surface feature detection and articulated motion tracking, which is regularized by a statistical human body model [26]. We also propose the idea of a Consensus Mesh (CMesh) which is the 3D template of a person created from a single view point. We demonstrate tracking results on challenging poses and argue that using CMesh along with statistical body models can improve tracking accuracies. Quantitative evaluation of our dense body tracking shows that our method has very little drift which is improved by the usage of CMesh.

Abstract

The ability of machine-based agents to play games in human-like fashion is considered a benchmark of progress in AI. In this paper, we introduce the first computational model aimed at Pictionary, the popular word-guessing social game. We first introduce Sketch-QA, an elementary version of Visual Question Answering task. Styled after Pictionary, Sketch-QA uses incrementally accumulated sketch stroke sequences as visual data. Notably, Sketch-QA involves asking a fixed question (" What object is being drawn?") and gathering open-ended guess-words from human guessers. To mimic Pictionary-style guessing, we propose a deep neural model which generates guess-words in response to temporally evolving human-drawn sketches. Our model even makes human-like mistakes while guessing, thus amplifying the human mimicry factor. We evaluate our model on the large-scale guess-word dataset generated via Sketch-QA task and compare with various baselines. We also conduct a Visual Turing Test to obtain human impressions of the guess-words generated by humans and our model. Experimental results demonstrate the promise of our approach for Pictionary and similarly themed games.

Abstract

Given a target image as query, person re-identification systems retrieve a ranked list of candidate matches on a per-camera basis. In deployed systems, a human operator scans these lists and labels sighted targets by touch or mouse-based selection. However, classical re-id approaches generate per-camera lists independently. Therefore, target identifications by operator in a subset of cameras cannot be utilized to improve ranking of the target in remaining set of network cameras. To address this shortcoming, we propose a novel sequential multi-camera re-id approach. The proposed approach can accommodate human operator inputs and provides early gains via a monotonic improvement in target ranking. At the heart of our approach is a fusion function which operates on deep feature representations of query and candidate matches. We formulate an optimization procedure custom-designed to incrementally improve query representation. Since existing evaluation methods cannot be directly adopted to our setting, we also propose two novel evaluation protocols. The results on two large-scale re-id datasets (Market-1501, DukeMTMC-reID) demonstrate that our multi-camera method significantly outperforms baselines and other popular feature fusion schemes. Additionally, we conduct a comparative subject-based study of human operator performance. The superior operator performance enabled by our approach makes a compelling case for its integration into deployable video-surveillance systems.