AI RESEARCH

Take a Peek: Efficient Encoder Adaptation for Few-Shot Semantic Segmentation via LoRA

arXiv CS.CV

ArXi:2512.10521v2 Announce Type: replace Few-shot semantic segmentation (FSS) aims to segment novel classes in query images using only a small annotated 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