8 citations · 15 across the 9 of their papers we have counts for
9 papers
Source-free Semantic Regularization Learning for Semi-supervised Domain Adaptation
Xinyang Huang, Chuang Zhu, Ruiying Ren +2
Semi-supervised domain adaptation (SSDA) has been extensively researched due to its ability to improve classification performance and generalization ability of models by using a sm…
Learning from Different Samples: A Source-free Framework for Semi-supervised Domain Adaptation
Xinyang Huang, Chuang Zhu, Bowen Zhang +1
Semi-supervised domain adaptation (SSDA) has been widely studied due to its ability to utilize a few labeled target data to improve the generalization ability of the model. However…
Learning Robust Correlation with Foundation Model for Weakly-Supervised Few-Shot Segmentation
Xinyang Huang, Chuang Zhu, Kebin Liu +2
Existing few-shot segmentation (FSS) only considers learning support-query correlation and segmenting unseen categories under the precise pixel masks. However, the cost of a large…
RestNet: Boosting Cross-Domain Few-Shot Segmentation with Residual Transformation Network
Xinyang Huang, Chuang Zhu, Wenkai Chen
Cross-domain few-shot segmentation (CD-FSS) aims to achieve semantic segmentation in previously unseen domains with a limited number of annotated samples. Although existing CD-FSS…
Temporal Consistent Automatic Video Colorization via Semantic Correspondence
Yu Zhang, Siqi Chen, Mingdao Wang +4
Video colorization task has recently attracted wide attention. Recent methods mainly work on the temporal consistency in adjacent frames or frames with small interval. However, it…
A Self-Training Framework Based on Multi-Scale Attention Fusion for Weakly Supervised Semantic Segmentation
Guoqing Yang, Chuang Zhu, Yu Zhang
Weakly supervised semantic segmentation (WSSS) based on image-level labels is challenging since it is hard to obtain complete semantic regions. To address this issue, we propose a…
Semi-supervised Domain Adaptation via Prototype-based Multi-level Learning
Xinyang Huang, Chuang Zhu, Wenkai Chen
In semi-supervised domain adaptation (SSDA), a few labeled target samples of each class help the model to transfer knowledge representation from the fully labeled source domain to…
Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation
Chuang Zhu, Kebin Liu, Wenqi Tang +3
The divergence between labeled training data and unlabeled testing data is a significant challenge for recent deep learning models. Unsupervised domain adaptation (UDA) attempts to…
WUDA: Unsupervised Domain Adaptation Based on Weak Source Domain Labels
Shengjie Liu, Chuang Zhu, Wenqi Tang
Unsupervised domain adaptation (UDA) for semantic segmentation addresses the cross-domain problem with fine source domain labels. However, the acquisition of semantic labels has al…