1.6k citations
- Vi Technology (United States)US5 papers
- Chinese Academy of SciencesCN3 papers
- Tongji UniversityCN3 papers
- Beijing University of Posts and TelecommunicationsCN2 papers
- Hong Kong University of Science and TechnologyHK2 papers
- Tsinghua UniversityCN2 papers
- University of Science and Technology of ChinaCN2 papers
- Agency for Science, Technology and ResearchSG1 paper
- Australian National UniversityAU1 paper
- Beihang UniversityCN1 paper
- Beijing Institute of TechnologyCN1 paper
- Beijing Normal UniversityCN1 paper
12 papers · 1 filter
TP-LSD: Tri-Points Based Line Segment Detector
Siyu Huang, Fangbo Qin, Pengfei Xiong +3
This paper proposes a novel deep convolutional model, Tri-Points Based Line Segment Detector (TP-LSD), to detect line segments in an image at real-time speed. The previous related…
LabelEnc: A New Intermediate Supervision Method for Object Detection
Miao Hao, Yitao Liu, Xiangyu Zhang +1
In this paper we propose a new intermediate supervision method, named LabelEnc, to boost the training of object detection systems. The key idea is to introduce a novel label encodi…
Spherical Feature Transform for Deep Metric Learning
Yuke Zhu, Yan Bai, Yichen Wei
Data augmentation in feature space is effective to increase data diversity. Previous methods assume that different classes have the same covariance in their feature distributions.…
Prime-Aware Adaptive Distillation
Youcai Zhang, Zhonghao Lan, Yuchen Dai +4
Knowledge distillation(KD) aims to improve the performance of a student network by mimicing the knowledge from a powerful teacher network. Existing methods focus on studying what k…
Funnel Activation for Visual Recognition
Ningning Ma, Xiangyu Zhang, Jian Sun
We present a conceptually simple but effective funnel activation for image recognition tasks, called Funnel activation (FReLU), that extends ReLU and PReLU to a 2D activation by ad…
WeightNet: Revisiting the Design Space of Weight Networks
Ningning Ma, Xiangyu Zhang, Jiawei Huang +1
We present a conceptually simple, flexible and effective framework for weight generating networks. Our approach is general that unifies two current distinct and extremely effective…