Abstract
Few-shot semantic segmentation (FSS) aims to segment novel classes in query images using only a small annotated support set. While prior research has mainly focused on improving decoders, the encoder's limited ability to extract meaningful features for unseen classes remains a key bottleneck. In this work, we introduce \textit{Take a Peek} (TaP), a simple yet effective method that enhances encoder adaptability for both FSS and cross-domain FSS (CD-FSS). TaP leverages Low-Rank Adaptation (LoRA) to fine-tune the encoder on the support set with minimal computational overhead, enabling fast adaptation to novel classes while mitigating catastrophic forgetting. Our method is model-agnostic and can be seamlessly integrated into existing FSS pipelines. Extensive experiments across multiple benchmarks--including COCO $20^i$, Pascal $5^i$, and cross-domain datasets such as DeepGlobe, ISIC, and Chest X-ray--demonstrate that TaP consistently improves segmentation performance across diverse models and shot settings. Notably, TaP delivers significant gains in complex multi-class scenarios, highlighting its practical effectiveness in realistic settings. A rank sensitivity analysis also shows that strong performance can be achieved even with low-rank adaptations, ensuring computational efficiency. By addressing a critical limitation in FSS--the encoder's generalization to novel classes--TaP paves the way toward more robust, efficient, and generalizable segmentation systems. The code is available at this https URL.
Abstract (translated)
少样本语义分割（FSS）的目标是使用仅有的少量标注支持集，在查询图像中对新类别进行分割。尽管先前的研究主要集中在改进解码器上，但编码器提取未见过类别的有意义特征的能力有限仍然是一个关键瓶颈。在这项工作中，我们引入了“Take a Peek”（TaP），这是一种简单而有效的方法，用于增强FSS和跨域少样本语义分割（CD-FSS）中编码器的适应性。TaP利用低秩适配（LoRA）在支持集上微调编码器，并且计算开销极小，从而能够快速适应新类别同时减轻灾难性遗忘问题。我们的方法是模型无关的，并可以无缝地集成到现有的FSS流程中。 我们在多个基准测试数据集上的大量实验——包括COCO 20i、Pascal 5i和跨域数据集如DeepGlobe、ISIC和胸部X光片，证明了TaP能够显著提升各种模型在不同样本设置下的分割性能。特别地，在复杂的多类别场景中，TaP表现出明显的改进效果，突显其在实际环境中的实用性和有效性。 通过秩敏感性分析也表明，即使使用低秩适配也能实现强大的性能，确保计算效率。通过解决FSS的一个关键限制——编码器对新类别的泛化能力不足的问题，TaP为更加稳健、高效且具有一般性的分割系统铺平了道路。代码可在以下网址获取：[提供链接]
URL
https://arxiv.org/abs/2512.10521
