Discriminatively Trained And-Or Graph Models for Object Shape Detection

Abstract

In this paper, we investigate a novel reconfigurable part-based model, namely And-Or graph model, to recognize object shapes in images. Our proposed model consists of four layers: leaf-nodes at the bottom are local classifiers for detecting contour fragments; or-nodes above the leaf-nodes function as the switches to activate their child leaf-nodes, making the model reconfigurable during inference; and-nodes in a higher layer capture holistic shape deformations; one root-node on the top, which is also an or-node, activates one of its child and-nodes to deal with large global variations (e.g. different poses and views). We propose a novel structural optimization algorithm to discriminatively train the And-Or model from weakly annotated data. This algorithm iteratively determines the model structures (e.g. the nodes and their layouts) along with the parameter learning. On several challenging datasets, our model demonstrates the effectiveness to perform robust shape-based object detection against background clutter and outperforms the other state-of-the-art approaches. We also release a new shape database with annotations, which includes more than 1500 challenging shape instances, for recognition and detection.

15 pages, 14 figures, TPAMI 2014

References in corpus (1)

• Dynamical And-Or Graph Learning for Object Shape Modeling and Detection

Cited by in corpus (17)

• Bit-Scalable Deep Hashing with Regularized Similarity Learning for Image Retrieval and Person Re-identification
• Deep Human Parsing with Active Template Regression
• Few-Example Object Detection with Model Communication
• DISC: Deep Image Saliency Computing via Progressive Representation Learning
• A Deep Structured Model with Radius-Margin Bound for 3D Human Activity Recognition
• PISA: Pixelwise Image Saliency by Aggregating Complementary Appearance Contrast Measures with Edge-Preserving Coherence
• Object Detection with Deep Learning: A Review
• Content-Adaptive Sketch Portrait Generation by Decompositional Representation Learning
• PCN: Part and Context Information for Pedestrian Detection with CNNs
• Data-Driven Scene Understanding with Adaptively Retrieved Exemplars
• AOGNets: Compositional Grammatical Architectures for Deep Learning
• Multi-Granularity Reasoning for Social Relation Recognition from Images
• Human Pose Estimation from Depth Images via Inference Embedded Multi-task Learning
• Deep Feature Learning with Relative Distance Comparison for Person Re-identification
• Pushing the Limits of Deep CNNs for Pedestrian Detection
• Deep Boosting: Joint Feature Selection and Analysis Dictionary Learning in Hierarchy
• Integrated Inference and Learning of Neural Factors in Structural Support Vector Machines