Výsledky vyhledávání - "Wang, Changqi"

Report

PRCL: Probabilistic Representation Contrastive Learning for Semi-Supervised Semantic Segmentation

Autor: Xie, Haoyu, Wang, Changqi, Zhao, Jian, Liu, Yang, Dan, Jun, Fu, Chong, Sun, Baigui

Tremendous breakthroughs have been developed in Semi-Supervised Semantic Segmentation (S4) through contrastive learning. However, due to limited annotations, the guidance on unlabeled images is generated by the model itself, which inevitably exists n

Externí odkaz: http://arxiv.org/abs/2402.18117

Zobrazit plný text záznamu

Report

Space Engage: Collaborative Space Supervision for Contrastive-based Semi-Supervised Semantic Segmentation

Autor: Wang, Changqi, Xie, Haoyu, Yuan, Yuhui, Fu, Chong, Yue, Xiangyu

Semi-Supervised Semantic Segmentation (S4) aims to train a segmentation model with limited labeled images and a substantial volume of unlabeled images. To improve the robustness of representations, powerful methods introduce a pixel-wise contrastive

Externí odkaz: http://arxiv.org/abs/2307.09755

Zobrazit plný text záznamu

Report

Boosting Semi-Supervised Semantic Segmentation with Probabilistic Representations

Autor: Xie, Haoyu, Wang, Changqi, Zheng, Mingkai, Dong, Minjing, You, Shan, Fu, Chong, Xu, Chang

Recent breakthroughs in semi-supervised semantic segmentation have been developed through contrastive learning. In prevalent pixel-wise contrastive learning solutions, the model maps pixels to deterministic representations and regularizes them in the

Externí odkaz: http://arxiv.org/abs/2210.14670

Zobrazit plný text záznamu