activity
20192023
most citedCross-Image Relational Knowledge Distillation for Semantic Segmentation

9 citations · 15 across the 5 of their papers we have counts for

collaborators

12 papers

cs.SD2023

Team AcieLee: Technical Report for EPIC-SOUNDS Audio-Based Interaction Recognition Challenge 2023

Yuqi Li, Yizhi Luo, Xiaoshuai Hao +4

In this report, we describe the technical details of our submission to the EPIC-SOUNDS Audio-Based Interaction Recognition Challenge 2023, by Team "AcieLee" (username: Yuqi\_Li). T…

cs.CV20229 cited

Cross-Image Relational Knowledge Distillation for Semantic Segmentation

Chuanguang Yang, Helong Zhou, Zhulin An +3

Current Knowledge Distillation (KD) methods for semantic segmentation often guide the student to mimic the teacher's structured information generated from individual data samples.…

cs.CV20201 cited

Learning Heatmap-Style Jigsaw Puzzles Provides Good Pretraining for 2D Human Pose Estimation

Kun Zhang, Rui Wu, Ping Yao +7

The target of 2D human pose estimation is to locate the keypoints of body parts from input 2D images. State-of-the-art methods for pose estimation usually construct pixel-wise heat…

cs.CV2020

Softer Pruning, Incremental Regularization

Linhang Cai, Zhulin An, Chuanguang Yang +1

Network pruning is widely used to compress Deep Neural Networks (DNNs). The Soft Filter Pruning (SFP) method zeroizes the pruned filters during training while updating them in the…

cs.CV2020

Multi-view Contrastive Learning for Online Knowledge Distillation

Chuanguang Yang, Zhulin An, Yongjun Xu

Previous Online Knowledge Distillation (OKD) often carries out mutually exchanging probability distributions, but neglects the useful representational knowledge. We therefore propo…

cs.CV2020

Localizing Interpretable Multi-scale informative Patches Derived from Media Classification Task

Chuanguang Yang, Zhulin An, Xiaolong Hu +2

Deep convolutional neural networks (CNN) always depend on wider receptive field (RF) and more complex non-linearity to achieve state-of-the-art performance, while suffering the inc…