no code implementations • 11 Oct 2023 • Zhiwei Wang, Qiang Hu, Hongkuan Shi, Li He, Man He, Wenxuan Dai, Ting Li, Yitong Zhang, Dun Li, Mei Liu, Qiang Li
In response, we propose two innovative learning fashions, Improved Box-dice (IBox) and Contrastive Latent-Anchors (CLA), and combine them to train a robust box-supervised model IBoxCLA.
1 code implementation • 15 Oct 2022 • Hongkuan Shi, Zhiwei Wang, Ying Zhou, Dun Li, Xin Yang, Qiang Li
The learned knowledge flows across branches along two directions: a cross direction (disparity guides distribution in ACS) and a parallel direction (disparity guides disparity in APS).
no code implementations • 13 Jul 2022 • Shaokang Cai, Dezhi Han, Zibin Zheng, Dun Li, NoelCrespi
In addition, by integrating a once-through learning approach, the speed of semantics purification is accelerated while reducing the impact on the quality of replies.