2.7k citations · 8.7k across the 28 of their papers we have counts for
30 papers
Adaptive neighborhood Metric learning
Kun Song, Junwei Han, Gong Cheng +2
In this paper, we reveal that metric learning would suffer from serious inseparable problem if without informative sample mining. Since the inseparable samples are often mixed with…
Pixel Distillation: A New Knowledge Distillation Scheme for Low-Resolution Image Recognition
Guangyu Guo, Dingwen Zhang, Longfei Han +3
Previous knowledge distillation (KD) methods mostly focus on compressing network architectures, which is not thorough enough in deployment as some costs like transmission bandwidth…
Weakly Supervised Semantic Segmentation via Alternative Self-Dual Teaching
Dingwen Zhang, Wenyuan Zeng, Guangyu Guo +4
Current weakly supervised semantic segmentation (WSSS) frameworks usually contain the separated mask-refinement model and the main semantic region mining model. These approaches wo…
Background-Click Supervision for Temporal Action Localization
Le Yang, Junwei Han, Tao Zhao +3
Weakly supervised temporal action localization aims at learning the instance-level action pattern from the video-level labels, where a significant challenge is action-context confu…
Light Field Saliency Detection with Dual Local Graph Learning andReciprocative Guidance
Nian Liu, Wangbo Zhao, Dingwen Zhang +2
The application of light field data in salient object de-tection is becoming increasingly popular recently. The diffi-culty lies in how to effectively fuse the features within the…
Physically Explainable CNN for SAR Image Classification
Zhongling Huang, Xiwen Yao, Ying Liu +3
Integrating the special electromagnetic characteristics of Synthetic Aperture Radar (SAR) in deep neural networks is essential in order to enhance the explainability and physics aw…