Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection

2016/04/16 by Xiang Yu, Wongun Choi, Xiang, Yu +5 · 1 citation
Computer Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human Pose and Action Recognition #Video Surveillance and Tracking Methods

paper · pdf · doi:10.48550/arxiv.1604.04693

openalex publication_date 2016/04/16 · openalex created_date 2019/06/27 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Robust Real-Time Face Detection

Cited by

• Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages

Related

• R-CNN minus R
• Object Detection based on Region Decomposition and Assembly
• Detecting and Grouping Identical Objects for Region Proposal and Classification
• Relief R-CNN : Utilizing Convolutional Features for Fast Object Detection
• CoupleNet: Coupling Global Structure with Local Parts for Object\n Detection