Vibhav Vineet

Conditional Random Fields as Recurrent Neural Networks

Pixel-level labelling tasks, such as semantic segmentation, play a central role in image understanding. Recent approaches have attempted to harness the capabilities of deep learning techniques for image recognition to tackle pixel-level labelling tasks. One central issue in this methodology is the limited capacity of deep learning techniques to delineate visual objects. To solve this problem, we introduce a new form of convolutional neural network that combines the strengths of Convolutional Neural Networks (CNNs) and Conditional Random Fields (CRFs)-based probabilistic graphical modelling. To this end, we formulate Conditional Random Fields with Gaussian pairwise potentials and mean-field approximate inference as Recurrent Neural Networks. This network, called CRF-RNN, is then plugged in as a part of a CNN to obtain a deep network that has desirable properties of both CNNs and CRFs. Importantly, our system fully integrates CRF modelling with CNNs, making it possible to train the whole deep network end-to-end with the usual back-propagation algorithm, avoiding offline post-processing methods for object delineation. We apply the proposed method to the problem of semantic image segmentation, obtaining top results on the challenging Pascal VOC 2012 segmentation benchmark.

The Visual Object Tracking VOT2014 Challenge Results

Visual tracking has attracted a significant attention in the last few decades. The recent surge in the number of publications on tracking-related problems have made it almost impossible to follow the developments in the field. One of the reasons is that there is a lack of commonly accepted annotated data-sets and standardized evaluation protocols that would allow objective comparison of different tracking methods. To address this issue, the Visual Object Tracking (VOT) workshop was organized in conjunction with ICCV2013. Researchers from academia as well as industry were invited to participate in the first VOT2013 challenge which aimed at single-object visual trackers that do not apply pre-learned models of object appearance (model-free). Presented here is the VOT2013 benchmark dataset for evaluation of single-object visual trackers as well as the results obtained by the trackers competing in the challenge. In contrast to related attempts in tracker benchmarking, the dataset is labeled per-frame by visual attributes that indicate occlusion, illumination change, motion change, size change and camera motion, offering a more systematic comparison of the trackers. Furthermore, we have designed an automated system for performing and evaluating the experiments. We present the evaluation protocol of the VOT2013 challenge and the results of a comparison of 27 trackers on the benchmark dataset. The dataset, the evaluation tools and the tracker rankings are publicly available from the challenge website (http://votchallenge.net).

Efficient Salient Region Detection with Soft Image Abstraction

Detecting visually salient regions in images is one of the fundamental problems in computer vision. We propose a novel method to decompose an image into large scale perceptually homogeneous elements for efficient salient region detection, using a soft image abstraction representation. By considering both appearance similarity and spatial distribution of image pixels, the proposed representation abstracts out unnecessary image details, allowing the assignment of comparable saliency values across similar regions, and producing perceptually accurate salient region detection. We evaluate our salient region detection approach on the largest publicly available dataset with pixel accurate annotations. The experimental results show that the proposed method outperforms 18 alternate methods, reducing the mean absolute error by 25.2% compared to the previous best result, while being computationally more efficient.

Struck: Structured Output Tracking with Kernels

Adaptive tracking-by-detection methods are widely used in computer vision for tracking arbitrary objects. Current approaches treat the tracking problem as a classification task and use online learning techniques to update the object model. However, for these updates to happen one needs to convert the estimated object position into a set of labelled training examples, and it is not clear how best to perform this intermediate step. Furthermore, the objective for the classifier (label prediction) is not explicitly coupled to the objective for the tracker (estimation of object position). In this paper, we present a framework for adaptive visual object tracking based on structured output prediction. By explicitly allowing the output space to express the needs of the tracker, we avoid the need for an intermediate classification step. Our method uses a kernelised structured output support vector machine (SVM), which is learned online to provide adaptive tracking. To allow our tracker to run at high frame rates, we (a) introduce a budgeting mechanism that prevents the unbounded growth in the number of support vectors that would otherwise occur during tracking, and (b) show how to implement tracking on the GPU. Experimentally, we show that our algorithm is able to outperform state-of-the-art trackers on various benchmark videos. Additionally, we show that we can easily incorporate additional features and kernels into our framework, which results in increased tracking performance.

SemanticPaint: Interactive 3D Labeling and Learning at your Fingertips

We present a new interactive and online approach to 3D scene understanding. Our system, SemanticPaint, allows users to simultaneously scan their environment whilst interactively segmenting the scene simply by reaching out and touching any desired object or surface. Our system continuously learns from these segmentations, and labels new unseen parts of the environment. Unlike offline systems where capture, labeling, and batch learning often take hours or even days to perform, our approach is fully online. This provides users with continuous live feedback of the recognition during capture, allowing to immediately correct errors in the segmentation and/or learning—a feature that has so far been unavailable to batch and offline methods. This leads to models that are tailored or personalized specifically to the users environments and object classes of interest, opening up the potential for new applications in augmented reality, interior design, and human/robot navigation. It also provides the ability to capture substantial labeled 3D datasets for training large-scale visual recognition systems.

Filter-Based mean-field inference for random fields with higher-order terms and product label-spaces

Recently, a number of cross bilateral filtering methods have been proposed for solving multi-label problems in computer vision, such as stereo, optical flow and object class segmentation that show an order of magnitude improvement in speed over previous methods. These methods have achieved good results despite using models with only unary and/or pairwise terms. However, previous work has shown the value of using models with higher-order terms e.g. to represent label consistency over large regions, or global co-occurrence relations. We show how these higher-order terms can be formulated such that filter-based inference remains possible. We demonstrate our techniques on joint stereo and object labeling problems, as well as object class segmentation, showing in addition for joint object-stereo labeling how our method provides an efficient approach to inference in product label-spaces. We show that we are able to speed up inference in these models around 10-30 times with respect to competing graph-cut/move-making methods, as well as maintaining or improving accuracy in all cases. We show results on PascalVOC-10 for object class segmentation, and Leuven for joint object-stereo labeling.

ImageSpirit: Verbal Guided Image Parsing

Humans describe images in terms of nouns and adjectives while algorithms operate on images represented as sets of pixels. Bridging this gap between how humans would like to access images versus their typical representation is the goal of image parsing, which involves assigning object and attribute labels to pixels. In this article we propose treating nouns as object labels and adjectives as visual attribute labels. This allows us to formulate the image parsing problem as one of jointly estimating per-pixel object and attribute labels from a set of training images. We propose an efficient (interactive time) solution. Using the extracted labels as handles, our system empowers a user to verbally refine the results. This enables hands-free parsing of an image into pixel-wise object/attribute labels that correspond to human semantics. Verbally selecting objects of interest enables a novel and natural interaction modality that can possibly be used to interact with new generation devices (e.g., smartphones, Google Glass, livingroom devices). We demonstrate our system on a large number of real-world images with varying complexity. To help understand the trade-offs compared to traditional mouse-based interactions, results are reported for both a large-scale quantitative evaluation and a user study.

Filter-Based Mean-Field Inference for Random Fields with Higher-Order Terms and Product Label-Spaces

Recently, a number of cross bilateral filtering methods have been proposed for solving multi-label problems in computer vision, such as stereo, optical flow and object class segmentation that show an order of magnitude improvement in speed over previous methods. These methods have achieved good results despite using models with only unary and/or pairwise terms. However, previous work has shown the value of using models with higher-order terms e.g. to represent label consistency over large regions, or global co-occurrence relations. We show how these higher-order terms can be formulated such that filter-based inference remains possible. We demonstrate our techniques on joint stereo and object labelling problems, as well as object class segmentation, showing in addition for joint object-stereo labelling how our method provides an efficient approach to inference in product label-spaces. We show that we are able to speed up inference in these models around 10–30 times with respect to competing graph-cut/move-making methods, as well as maintaining or improving accuracy in all cases. We show results on PascalVOC-10 for object class segmentation, and Leuven for joint object-stereo labelling.

Human Instance Segmentation from Video using Detector-based Conditional Random Fields

In this work, we propose a method for instance based human segmentation in images and videos, extending the recent detector-based conditional random field model of Ladicky et.al. Instance based human segmentation involves pixel level labeling of an image, partitioning it into distinct human instances and background. To achieve our goal, we add three new components to their framework. First, we include human partsbased detection potentials to take advantage of the structure present in human instances. Further, in order to generate a consistent segmentation from different human parts, we incorporate shape prior information, which biases the segmentation to characteristic overall human shapes. Also, we enhance the representative power of the energy function by adopting exemplar instance based matching terms, which helps our method to adapt easily to different human sizes and poses. Finally, we extensively evaluate our proposed method on the Buffy dataset with our new segmented ground truth images, and show a substantial improvement over existing CRF methods. These new annotations will be made available for future use as well.

PoseField: An Efficient Mean-Field Based Method for Joint Estimation of Human Pose, Segmentation, and Depth

Many models have been proposed to estimate human pose and segmentation by leveraging information from several sources. A standard approach is to formulate it in a dual decomposition framework. However, these models generally suffer from the problem of high computational complexity. In this work, we propose PoseField, a new highly efficient filter-based mean-field inference approach for jointly estimating human segmentation, pose, per-pixel body parts, and depth given stereo pairs of images. We extensively evaluate the efficiency and accuracy offered by our approach on H2View [1], and Buffy [2] datasets. We achieve 20 to 70 times speedup compared to the current state-of-the-art methods, as well as achieving better accuracy in all these cases.