Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection
This addresses object detection and pose estimation for computer vision applications, with incremental improvements through subcategory integration.
The paper tackles the bottleneck of region proposal in CNN-based object detection under scale variation, occlusion, or truncation, and introduces subcategory-aware CNNs that achieve state-of-the-art performance on detection and pose estimation benchmarks.
In CNN-based object detection methods, region proposal becomes a bottleneck when objects exhibit significant scale variation, occlusion or truncation. In addition, these methods mainly focus on 2D object detection and cannot estimate detailed properties of objects. In this paper, we propose subcategory-aware CNNs for object detection. We introduce a novel region proposal network that uses subcategory information to guide the proposal generating process, and a new detection network for joint detection and subcategory classification. By using subcategories related to object pose, we achieve state-of-the-art performance on both detection and pose estimation on commonly used benchmarks.