Haitao Wei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Haitao Wei has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Jianming Liu
Jiangxi Normal University
4 shared publications - Wenlong Qiu
School of Digital Industry, Jiangxi Normal University, Shangrao, Jiangxi, China
3 shared publications - Tong Chen
Jiangxi Normal University
2 shared publications - Chunyang Li
Jiangxi Normal University
1 shared publication - Xuhua Liu
Jiangxi Normal University
1 shared publication
Latest Publications
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 5150-5159
Textual and Visual Guided Task Adaptation for Source-Free Cross-Domain Few-Shot Segmentation
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 5150-5159
Open AccessTextual and Visual Guided Task Adaptation for Source-Free Cross-Domain Few-Shot Segmentation
- Open Access
Textual and Visual Guided Task Adaptation for Source-Free Cross-Domain Few-Shot Segmentation
Few-Shot Segmentation(FSS) aims to efficient segmentation of new objects with few labeled samples. However, its performance significantly degrades when domain discrepancies exist between training and deployment. Cross-Domain Few-Shot Segmentation(CD-FSS) is proposed to mitigate such performance degradation. Current CD-FSS methods primarily sought to develop segmentation models on a source domain capable of cross-domain generalization. However, driven by escalating concerns over data privacy and the imperative to minimize data transfer and training expenses, the development of source-free CD-FSS approaches has become essential. In this work, we propose a source-free CD-FSS method that leverages both textual and visual information to facilitate target domain task adaptation without requiring source domain data. Specifically, we first append Task-Specific Attention Adapters (TSAA) to the feature pyramid of a pretrained backbone, which adapt multi-level features extracted from the shared pre-trained backbone to the target task. Then, the parameters of the TSAA are trained through a Visual-Visual Embedding Alignment (VVEA) module and a Text-Visual Embedding Alignment (TVEA) module. The VVEA module utilizes global-local visual features to align image features across different views, while the TVEA module leverages textual priors from pre-aligned multi-modal features (e.g., from CLIP) to guide cross-modal adaptation. By combining the outputs of these modules through dense comparison operations and subsequent fusion via skip connections, our method produces refined prediction masks. Under both 1-shot and 5-shot settings, the proposed approach achieves average segmentation accuracy improvements of 2.18\% and 4.11\%, respectively, across four cross-domain datasets, significantly outperforming state-of-the-art CD-FSS methods. Code are available at https://github.com/ljm198134/TVGTANet.
Open AccessTextual and Visual Guided Task Adaptation for Source-Free Cross-Domain Few-Shot Segmentation
Few-Shot Segmentation(FSS) aims to efficient segmentation of new objects with few labeled samples. However, its performance significantly degrades when domain discrepancies exist between training and deployment. Cross-Domain Few-Shot Segmentation(CD-FSS) is proposed to mitigate such performance degradation. Current CD-FSS methods primarily sought to develop segmentation models on a source domain capable of cross-domain generalization. However, driven by escalating concerns over data privacy and the imperative to minimize data transfer and training expenses, the development of source-free CD-FSS approaches has become essential. In this work, we propose a source-free CD-FSS method that leverages both textual and visual information to facilitate target domain task adaptation without requiring source domain data. Specifically, we first append Task-Specific Attention Adapters (TSAA) to the feature pyramid of a pretrained backbone, which adapt multi-level features extracted from the shared pre-trained backbone to the target task. Then, the parameters of the TSAA are trained through a Visual-Visual Embedding Alignment (VVEA) module and a Text-Visual Embedding Alignment (TVEA) module. The VVEA module utilizes global-local visual features to align image features across different views, while the TVEA module leverages textual priors from pre-aligned multi-modal features (e.g., from CLIP) to guide cross-modal adaptation. By combining the outputs of these modules through dense comparison operations and subsequent fusion via skip connections, our method produces refined prediction masks. Under both 1-shot and 5-shot settings, the proposed approach achieves average segmentation accuracy improvements of 2.18\% and 4.11\%, respectively, across four cross-domain datasets, significantly outperforming state-of-the-art CD-FSS methods. Code are available at https://github.com/ljm198134/TVGTANet.
- 8 December 2024
- Published by Springer Nature
- p. 320-336
TGCM: Cross-Domain Few-Shot Semantic Segmentation via One-Shot Target Guided CutMix
- 8 December 2024
- Published by Springer Nature
- p. 320-336
TGCM: Cross-Domain Few-Shot Semantic Segmentation via One-Shot Target Guided CutMix
- 14 August 2024
- Published by Springer Nature
- p. 286-297
Cross-Domain Few-Shot Fine-Grained Classification Based on Local-Global Semantic Consistency and Earth Mover’s Distance
- 14 August 2024
- Published by Springer Nature
- p. 286-297
Cross-Domain Few-Shot Fine-Grained Classification Based on Local-Global Semantic Consistency and Earth Mover’s Distance