Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection

16 Apr 2016  ·  Yu Xiang, Wongun Choi, Yuanqing Lin, Silvio Savarese ·

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.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Vehicle Pose Estimation KITTI Cars Hard SubCNN Average Orientation Similarity 78.68 # 4
Object Detection PASCAL VOC 2007 subCNN MAP 68.5% # 24

Methods


No methods listed for this paper. Add relevant methods here