no code implementations • 23 Mar 2024 • Xiaoqiang Yan, Zhixiang Jin, Fengshou Han, Yangdong Ye
In this work, we propose a new differentiable information bottleneck (DIB) method, which provides a deterministic and analytical MVC solution by fitting the mutual information without the necessity of variational approximation.
no code implementations • 23 Mar 2024 • Xiaoqiang Yan, Yingtao Gan, Yiqiao Mao, Yangdong Ye, Hui Yu
Finally, a three-step alternate optimization is proposed, in which the category memory library and consensus partition matrix are optimized.
no code implementations • CVPR 2017 • Xiaoqiang Yan, Shizhe Hu, Yangdong Ye
In this work, we present a novel and effective Multi-Task Information Bottleneck (MTIB) clustering method, which is capable of exploring the shared information between multiple action clustering tasks to improve the performance of individual task.