Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection

2016-04-16 · 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 BibTeX arXiv:1604.04693

Code (1)

xiaohaoChen/rrc_detection

Tasks

2D Object Detection General ClassificationObjectobject-detection Object Detection Pose EstimationRegion ProposalVehicle Pose Estimation

Subcategory-Aware Object Classification

2013-06-01 · CVPR 2013 6 · Jian Dong, Wei Xia, Qiang Chen, Jianshi Feng 외

In this paper, we introduce a subcategory-aware object classification framework to boost category level object classification performance. Motivated by the observation of considerable intra-class diversities and inter-cl…

Classification General Classification Object

Scale-aware Pixel-wise Object Proposal Networks

2016-01-19 · Zequn Jie, Xiaodan Liang, Jiashi Feng, Wen Feng Lu 외

Object proposal is essential for current state-of-the-art object detection pipelines. However, the existing proposal methods generally fail in producing results with satisfying localization accuracy. The case is even wor…

Object object-detection Object Detection Philosophy

Multi-scale Location-aware Kernel Representation for Object Detection

2018-04-02 · CVPR 2018 6 · Hao Wang, Qilong Wang, Mingqi Gao, Peihua Li 외

Although Faster R-CNN and its variants have shown promising performance in object detection, they only exploit simple first-order representation of object proposals for final classification and regression. Recent classif…

General Classification Object object-detection Object Detection

Domain Adaptive Scene Text Detection via Subcategorization

2022-12-01 · Zichen Tian, Chuhui Xue, Jingyi Zhang, Shijian Lu

Most existing scene text detectors require large-scale training data which cannot scale well due to two major factors: 1) scene text images often have domain-specific distributions; 2) collecting large-scale annotated sc…

Scene Text Detection Text Detection vehicle detection

Objectness Scoring and Detection Proposals in Forward-Looking Sonar Images with Convolutional Neural Networks

2017-09-08 · Matias Valdenegro-Toro

Forward-looking sonar can capture high resolution images of underwater scenes, but their interpretation is complex. Generic object detection in such images has not been solved, specially in cases of small and unknown obj…

Object object-detection Object Detection