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

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

URL: http://arxiv.org/abs/2512.10521v1
Date: Thu, 11 Dec 2025 10:47:01 GMT
Title: Take a Peek: Efficient Encoder Adaptation for Few-Shot Semantic Segmentation via LoRA
Authors: Pasquale De Marinis, Gennaro Vessio, Giovanna Castellano,
Abstract summary: Few-shot semantic segmentation (FSS) aims to segment novel classes in query images using only a small support set.<n>We introduce textitTake a Peek (TaP), a method that enhances encoder adaptability for both FSS and cross-domain FSS.
Score: 10.406945969691781
License: http://creativecommons.org/licenses/by/4.0/
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 https://github.com/pasqualedem/TakeAPeek.

Related papers

EfficientFSL: Enhancing Few-Shot Classification via Query-Only Tuning in Vision Transformers [4.880377460177786]
Large models such as Vision Transformers (ViTs) have demonstrated remarkable superiority over smaller architectures like ResNet in few-shot classification.<n>We propose EfficientFSL, a query-only fine-tuning framework tailored specifically for few-shot classification with ViT.<n>With minimal trainable parameters, EfficientFSL achieves state-of-the-art performance on four in-domain few-shot datasets and six cross-domain datasets.
arXiv Detail & Related papers (2026-01-13T12:33:02Z)
Rethinking Autoregressive Models for Lossless Image Compression via Hierarchical Parallelism and Progressive Adaptation [75.58269386927076]
Autoregressive (AR) models are often dismissed as impractical due to prohibitive computational cost.<n>This work re-thinks this paradigm, introducing a framework built on hierarchical parallelism and progressive adaptation.<n> Experiments on diverse datasets (natural, satellite, medical) validate that our method achieves new state-of-the-art compression.
arXiv Detail & Related papers (2025-11-14T06:27:58Z)
GLiClass: Generalist Lightweight Model for Sequence Classification Tasks [49.2639069781367]
We propose GLiClass, a novel method that adapts the GLiNER architecture for sequence classification tasks.<n>Our approach achieves strong accuracy and efficiency comparable to embedding-based methods, while maintaining the flexibility needed for zero-shot and few-shot learning scenarios.
arXiv Detail & Related papers (2025-08-11T06:22:25Z)
Semi-supervised Semantic Segmentation with Multi-Constraint Consistency Learning [81.02648336552421]
We propose a Multi-Constraint Consistency Learning approach to facilitate the staged enhancement of the encoder and decoder.<n>Self-adaptive feature masking and noise injection are designed in an instance-specific manner to perturb the features for robust learning of the decoder.<n> Experimental results on Pascal VOC2012 and Cityscapes datasets demonstrate that our proposed MCCL achieves new state-of-the-art performance.
arXiv Detail & Related papers (2025-03-23T03:21:33Z)
Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance Insights [8.725446812770791]
This paper focuses on source-free domain adaptation for object detection in computer vision. Recent research has proposed various solutions for Source-Free Object Detection (SFOD)
arXiv Detail & Related papers (2024-07-10T12:18:38Z)
Rethinking Few-shot 3D Point Cloud Semantic Segmentation [62.80639841429669]
This paper revisits few-shot 3D point cloud semantic segmentation (FS-PCS) We focus on two significant issues in the state-of-the-art: foreground leakage and sparse point distribution. To address these issues, we introduce a standardized FS-PCS setting, upon which a new benchmark is built.
arXiv Detail & Related papers (2024-03-01T15:14:47Z)
Adaptive FSS: A Novel Few-Shot Segmentation Framework via Prototype Enhancement [6.197356908000006]
The Few-Shot (FSS) aims to accomplish the novel class segmentation task with a few annotated images. We propose a novel framework based on the adapter mechanism, namely Adaptive FSS, which can efficiently adapt the existing FSS model to the novel classes. Our approach is compatible with diverse FSS methods with different backbones by simply inserting PAM between the layers of the encoder.
arXiv Detail & Related papers (2023-12-25T14:03:38Z)
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation [63.910211095033596]
Recently few-shot segmentation (FSS) has been extensively developed. This paper proposes a fresh and straightforward insight to alleviate the problem. In light of the unique nature of the proposed approach, we also extend it to a more realistic but challenging setting.
arXiv Detail & Related papers (2022-03-15T03:08:27Z)
Large-scale Optimization of Partial AUC in a Range of False Positive Rates [51.12047280149546]
The area under the ROC curve (AUC) is one of the most widely used performance measures for classification models in machine learning. We develop an efficient approximated gradient descent method based on recent practical envelope smoothing technique. Our proposed algorithm can also be used to minimize the sum of some ranked range loss, which also lacks efficient solvers.
arXiv Detail & Related papers (2022-03-03T03:46:18Z)
Prior Guided Feature Enrichment Network for Few-Shot Segmentation [64.91560451900125]
State-of-the-art semantic segmentation methods require sufficient labeled data to achieve good results. Few-shot segmentation is proposed to tackle this problem by learning a model that quickly adapts to new classes with a few labeled support samples. Theses frameworks still face the challenge of generalization ability reduction on unseen classes due to inappropriate use of high-level semantic information.
arXiv Detail & Related papers (2020-08-04T10:41:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.