Unimatch v2: Pushing the limit of semi-supervised semantic segmentation

L Yang, Z Zhao, H Zhao - IEEE Transactions on Pattern …, 2025 - ieeexplore.ieee.org
Semi-supervised semantic segmentation (SSS) aims at learning rich visual knowledge from
cheap unlabeled images to enhance semantic segmentation capability. Among recent …

Triplet adaptation framework for robust semi-supervised learning

R Hou, H Chang, B Ma, S Shan… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Semi-supervised learning (SSL) suffers from severe performance degradation when labeled
and unlabeled data come from inconsistent and imbalanced distribution. Nonetheless, there …

UMFC: Unsupervised Multi-Domain Feature Calibration for Vision-Language Models

J Liang, R Hou, M Hu, H Chang, S Shan… - arxiv preprint arxiv …, 2024 - arxiv.org
Pre-trained vision-language models (eg, CLIP) have shown powerful zero-shot transfer
capabilities. But they still struggle with domain shifts and typically require labeled data to …

Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness

J Li, H Huang, Y Zhang, P Xu, X Chen, R Song… - arxiv preprint arxiv …, 2024 - arxiv.org
Recently, there has been significant interest in replacing the reward model in Reinforcement
Learning with Human Feedback (RLHF) methods for Large Language Models (LLMs), such …