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

arXiv: https://arxiv.org/abs/2512.10521 · HTML: https://mlsanity.com/paper/2512.10521/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 39 references that are in the map.
- First posted on arXiv 11 Dec 2025.

## Builds on (most cited first, 22 of 22)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1902.03368/) (2019)
- [PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment](https://mlsanity.com/paper/1908.06391/) (2019)
- [One-Shot Learning for Semantic Segmentation](https://mlsanity.com/paper/1709.03410/) (2017)
- [DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images](https://mlsanity.com/paper/1805.06561/) (2018)
- [Hypercorrelation Squeeze for Few-Shot Segmentation](https://mlsanity.com/paper/2104.01538/) (2021)
- [Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?](https://mlsanity.com/paper/2012.06166/) (2020)
- [Learning What Not to Segment: A New Perspective on Few-Shot Segmentation](https://mlsanity.com/paper/2203.07615/) (2022)
- [Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation](https://mlsanity.com/paper/2309.14859/) (2023)
- [Hierarchical Dense Correlation Distillation for Few-Shot Segmentation](https://mlsanity.com/paper/2303.14652/) (2023)
- [Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation](https://mlsanity.com/paper/2207.08549/) (2022)
- [Feature-Proxy Transformer for Few-Shot Segmentation](https://mlsanity.com/paper/2210.06908/) (2022)
- [Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning](https://mlsanity.com/paper/2206.06122/) (2022)
- [Revisiting Few-Shot Object Detection with Vision-Language Models](https://mlsanity.com/paper/2312.14494/) (2023)
- [A Novel Benchmark for Few-Shot Semantic Segmentation in the Era of Foundation Models](https://mlsanity.com/paper/2401.11311/) (2024)
- [Cross-Domain Few-Shot Semantic Segmentation via Doubly Matching Transformation](https://mlsanity.com/paper/2405.15265/) (2024)
- [MFNet: Multi-class Few-shot Segmentation Network with Pixel-wise Metric Learning](https://mlsanity.com/paper/2111.00232/) (2021)
- [Adaptive FSS: A Novel Few-Shot Segmentation Framework via Prototype Enhancement](https://mlsanity.com/paper/2312.15731/) (2023)
- [Label Anything: Multi-Class Few-Shot Semantic Segmentation with Visual Prompts](https://mlsanity.com/paper/2407.02075/) (2024)

## Built on by (most cited first, 1 of 1)

- [Path-Decoupled Hyperbolic Flow Matching for Few-Shot Adaptation](https://mlsanity.com/paper/2602.20479/) (2026)

## Abstract (arXiv)

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 textitTake a Peek (TaP), a simple yet effective method that enhances encoder adaptability for both FSS and cross-domain FSS revby inducing a lightweight textitfeature-space shift conditioned on the support set. TaP leverages Low-Rank Adaptation 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 20i, Pascal 5i, 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, thereby 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 https://github.com/pasqualedem/TakeAPeek.