1 code implementation • 17 Aug 2023 • Xihong Yang, Jiaqi Jin, Siwei Wang, Ke Liang, Yue Liu, Yi Wen, Suyuan Liu, Sihang Zhou, Xinwang Liu, En Zhu
Then, a global contrastive calibration loss is proposed by aligning the view feature similarity graph and the high-confidence pseudo-label graph.
no code implementations • CVPR 2023 • Jiaqi Jin, Siwei Wang, Zhibin Dong, Xinwang Liu, En Zhu
The success of existing multi-view clustering relies on the assumption of sample integrity across multiple views.
no code implementations • ICCV 2023 • Zhibin Dong, Siwei Wang, Jiaqi Jin, Xinwang Liu, En Zhu
However, most existing deep clustering approaches are dedicated to merging and exploring the consistent latent representation across multiple views while overlooking the abundant complementary information in each view.
1 code implementation • 30 May 2022 • Siwei Wang, Xinwang Liu, Suyuan Liu, Jiaqi Jin, Wenxuan Tu, Xinzhong Zhu, En Zhu
Under multi-view scenarios, generating correct correspondences could be extremely difficult since anchors are not consistent in feature dimensions.
1 code implementation • 14 Feb 2022 • Yu Chen, Jiaqi Jin, Hui Zhao, Pengjie Wang, Guojun Liu, Jian Xu, Bo Zheng
Moreover, to estimate CVR upon the freshly observed but biased distribution with fake negatives, the importance sampling is widely used to reduce the distribution bias.