Learning a Dictionary of Shape Epitomes with Applications to Image Labeling

By Liang-Chieh Chen, George Papandreou, Alan L. Yuille. 2013

17 citations recorded by the source corpus.

The first main contribution of this paper is a novel method for representing images based on a dictionary of shape epitomes. These shape epitomes represent the local edge structure of the image and include hidden variables to encode shift and rotations. They are learnt in an unsupervised manner from ground truth edges. This dictionary is compact but is also able to capture the typical shapes of edges in natural images. In this paper, we illustrate the shape epitomes by applying them to the image labeling task. In other work, described in the supplementary material, we apply them to edge detection and image modeling. We apply shape epitomes to image labeling by using Conditional Random Field (CRF) Models. They are alternatives to the super pixel or pixel representations used in most CRFs. In our approach, the shape of an image patch is encoded by a shape epitome from the dictionary. Unlike the super pixel representation, our method avoids making early decisions which cannot be reversed. Our resulting hierarchical CRFs efficiently capture both local and global class co-occurrence properties. We demonstrate its quantitative and qualitative properties of our approach with image labeling experiments on two standard datasets: MSRC-21 and Stanford Background.

Subfields: Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs (2016, methodology): “of segments [29], [30], [31], [32], [33], we use the fully connected pairwise CRF proposed by [22] for its efficient computation, and ability to capture fine edge details while also catering for long range dependencies.”
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs (2014, methodology): “…et al., 2009; Lempitsky et al., 2011) and/or high-order dependencies of segments (Delong et al., 2012; Gonfaus et al., 2010; Kohli et al., 2009; Chen et al., 2013; Wang et al., 2015), we use the fully connected pairwise CRF proposed by Kr ¨ ahenb ¨ uhl & Koltun (2011) for its efﬁcient…”
Semantic part segmentation using compositional model combining shape and appearance (2014, background): “The past few years have witnessed significant progress on various object-level visual recognition tasks, such as object detection [13, 17], object segmentation [5, 1, 7], etc.”