Adaptive Attention Distillation for Robust Few-Shot Segmentation under Environmental Perturbations

TL;DR

This paper introduces an environment-robust few-shot segmentation benchmark and proposes an Adaptive Attention Distillation method to improve model robustness in complex real-world scenarios, demonstrating significant performance gains.

Contribution

It establishes a new benchmark for environment-robust FSS and proposes a novel AAD method that enhances focus on targets under challenging conditions.

Findings

AAD improves mIoU by 3.3% to 8.5% across datasets

The benchmark covers eight datasets with complex environmental factors

AAD demonstrates superior generalization in real-world scenarios

Abstract

Few-shot segmentation (FSS) aims to rapidly learn novel class concepts from limited examples to segment specific targets in unseen images, and has been widely applied in areas such as medical diagnosis and industrial inspection. However, existing studies largely overlook the complex environmental factors encountered in real world scenarios-such as illumination, background, and camera viewpoint-which can substantially increase the difficulty of test images. As a result, models trained under laboratory conditions often fall short of practical deployment requirements. To bridge this gap, in this paper, an environment-robust FSS setting is introduced that explicitly incorporates challenging test cases arising from complex environments-such as motion blur, small objects, and camouflaged targets-to enhance model's robustness under realistic, dynamic conditions. An environment robust FSS benchmark (ER-FSS) is established, covering eight datasets across multiple real world scenarios. In addition, an Adaptive Attention Distillation (AAD) method is proposed, which repeatedly contrasts and distills key shared semantics between known (support) and unknown (query) images to derive class-specific attention for novel categories. This strengthens the model's ability to focus on the correct targets in complex environments, thereby improving environmental robustness. Comparative experiments show that AAD improves mIoU by 3.3% - 8.5% across all datasets and settings, demonstrating superior performance and strong generalization. The source code and dataset are available at: https://github.com/guoqianyu-alberta/Adaptive-Attention-Distillation-for-FSS.