# Self-Disentanglement and Re-Composition for Cross-Domain Few-Shot Segmentation

arXiv: https://arxiv.org/abs/2506.02677 · HTML: https://mlsanity.com/paper/2506.02677/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jun 2025.

## Built on by (most cited first, 9 of 9)

- [Multimodal Model for Computational Pathology:Representation Learning and Image Compression](https://mlsanity.com/paper/2603.18660/) (2026)
- [Boosting SAM for Cross-Domain Few-Shot Segmentation via Conditional Point Sparsification](https://mlsanity.com/paper/2602.05218/) (2026)
- [Unify the Views: View-Consistent Prototype Learning for Few-Shot Segmentation](https://mlsanity.com/paper/2603.05952/) (2026)
- [Training-free Cross-domain Few-shot Segmentation via Robust Semantic Representation and Matching](https://mlsanity.com/paper/2606.24297/) (2026)
- [Cross-Domain Few-Shot Segmentation via Ordinary Differential Equations over Time Intervals](https://mlsanity.com/paper/2509.01299/) (2025)
- [Cross-Domain Few-Shot Segmentation via Multi-view Progressive Adaptation](https://mlsanity.com/paper/2602.05217/) (2026)
- [Selective, Regularized, and Calibrated: Harnessing Vision Foundation Models for Cross-Domain Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2605.19340/) (2026)
- [Hierarchical Spatial and Channel Aggregation for Cross-domain Few-shot Segmentation](https://mlsanity.com/paper/2606.24296/) (2026)
- [The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answering](https://mlsanity.com/paper/2608.04589/) (2026)

## Abstract (arXiv)

Cross-Domain Few-Shot Segmentation (CD-FSS) aims to transfer knowledge from a source-domain dataset to unseen target-domain datasets with limited annotations. Current methods typically compare the distance between training and testing samples for mask prediction. However, we find an entanglement problem exists in this widely adopted method, which tends to bind sourcedomain patterns together and make each of them hard to transfer. In this paper, we aim to address this problem for the CD-FSS task. We first find a natural decomposition of the ViT structure, based on which we delve into the entanglement problem for an interpretation. We find the decomposed ViT components are crossly compared between images in distance calculation, where the rational comparisons are entangled with those meaningless ones by their equal importance, leading to the entanglement problem. Based on this interpretation, we further propose to address the entanglement problem by learning to weigh for all comparisons of ViT components, which learn disentangled features and re-compose them for the CD-FSS task, benefiting both the generalization and finetuning. Experiments show that our model outperforms the state-of-the-art CD-FSS method by 1.92% and 1.88% in average accuracy under 1-shot and 5-shot settings, respectively.