解决跨域少样本分割中的特征纠缠问题，提升模型泛化能力。
Self-Disentanglement and Re-Composition for Cross-Domain Few-Shot Segmentation
- 通过分解ViT结构分析纠缠机制，发现距离计算中成分比较存在冗余
- 提出加权重组成方法，使模型在1-shot和5-shot下分别提升1.92%和1.88%
- 适合需要高效迁移学习的少样本图像分割场景
跨域少样本分割（CD-FSS）旨在将源域数据集的知识迁移到未见的目标域数据集，且标注有限。现有方法通常通过比较训练与测试样本间的距离进行掩码预测。我们发现该方法存在特征纠缠问题，导致源域模式被紧密绑定，难以有效迁移。本文首先基于ViT结构的自然分解，深入分析此问题：在距离计算中，不同图像间的组件被交叉比较，合理与无意义的比较因同等重要而相互干扰，引发纠缠。基于此，我们提出对所有组件比较进行学习加权，实现特征解耦与重组成，显著提升模型在微调与泛化上的表现。实验表明，我们的方法在1-shot和5-shot设置下，平均准确率分别优于当前最优方法1.92%和1.88%。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。