Parameter-Efficient Subspace Decoupling ViT for Mitigating Multi-Task Negative Transfer in Histological Scoring
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914615371235328 |
|---|---|
| author | Huang, Youhan Li, Jiajun Fang, Yilin Wang, Shuai Li, Chuheng |
| author_facet | Huang, Youhan Li, Jiajun Fang, Yilin Wang, Shuai Li, Chuheng |
| contents | Histological scoring is essential for diagnosing Non-Alcoholic Fatty Liver Disease (NAFLD), yet its automation remains challenging due to the high annotation cost and negative transfer among the strongly correlated NAFLD Activity Score (NAS) indicators in multi-task learning. To address this issue, we propose a subspace-decoupled multi-task Vision Transformer (ViT) that integrates lightweight task-specific Adapters with orthogonality-based constraints. This design constructs independent feature subspaces for steatosis, ballooning, and inflammation, effectively reducing task interference while retaining shared representations. We further construct a curated multi-task mouse NAFLD histology dataset with expert annotations for all NAS components. Experimental results demonstrate that the proposed method improves multi-task stability and generalization with substantially reduced computational cost compared to training separate single-task models. The code and the curated dataset have been prepared and will be made publicly available upon acceptance to support reproducibility. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_29852 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Parameter-Efficient Subspace Decoupling ViT for Mitigating Multi-Task Negative Transfer in Histological Scoring Huang, Youhan Li, Jiajun Fang, Yilin Wang, Shuai Li, Chuheng Computer Vision and Pattern Recognition Machine Learning Multimedia Histological scoring is essential for diagnosing Non-Alcoholic Fatty Liver Disease (NAFLD), yet its automation remains challenging due to the high annotation cost and negative transfer among the strongly correlated NAFLD Activity Score (NAS) indicators in multi-task learning. To address this issue, we propose a subspace-decoupled multi-task Vision Transformer (ViT) that integrates lightweight task-specific Adapters with orthogonality-based constraints. This design constructs independent feature subspaces for steatosis, ballooning, and inflammation, effectively reducing task interference while retaining shared representations. We further construct a curated multi-task mouse NAFLD histology dataset with expert annotations for all NAS components. Experimental results demonstrate that the proposed method improves multi-task stability and generalization with substantially reduced computational cost compared to training separate single-task models. The code and the curated dataset have been prepared and will be made publicly available upon acceptance to support reproducibility. |
| title | Parameter-Efficient Subspace Decoupling ViT for Mitigating Multi-Task Negative Transfer in Histological Scoring |
| topic | Computer Vision and Pattern Recognition Machine Learning Multimedia |
| url | https://arxiv.org/abs/2605.29852 |