Dynamical And-Or Graph Learning for Object Shape Modeling and Detection
This work addresses object shape modeling and detection in computer vision, offering a novel approach to improve accuracy in cluttered environments, though it appears incremental as it builds on existing part-based models and learning algorithms.
The paper tackles object shape detection by proposing a discriminative part-based model using an And-Or graph to handle large intra-class variance and background clutter, and it outperforms state-of-the-art methods on challenging databases like INRIA-Horse, ETHZ-Shape, and UIUC-People.
This paper studies a novel discriminative part-based model to represent and recognize object shapes with an "And-Or graph". We define this model consisting of three layers: the leaf-nodes with collaborative edges for localizing local parts, the or-nodes specifying the switch of leaf-nodes, and the root-node encoding the global verification. A discriminative learning algorithm, extended from the CCCP [23], is proposed to train the model in a dynamical manner: the model structure (e.g., the configuration of the leaf-nodes associated with the or-nodes) is automatically determined with optimizing the multi-layer parameters during the iteration. The advantages of our method are two-fold. (i) The And-Or graph model enables us to handle well large intra-class variance and background clutters for object shape detection from images. (ii) The proposed learning algorithm is able to obtain the And-Or graph representation without requiring elaborate supervision and initialization. We validate the proposed method on several challenging databases (e.g., INRIA-Horse, ETHZ-Shape, and UIUC-People), and it outperforms the state-of-the-arts approaches.