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

• URL: http://arxiv.org/abs/2601.03596v1
• Date: Wed, 07 Jan 2026 05:27:12 GMT
• Title: Adaptive Attention Distillation for Robust Few-Shot Segmentation under Environmental Perturbations
• Authors: Qianyu Guo, Jingrong Wu, Jieji Ren, Weifeng Ge, Wenqiang Zhang,
• Abstract summary: Few-shot segmentation (FSS) aims to rapidly learn novel class concepts from limited examples to segment specific targets in unseen images.<n>Existing studies largely overlook the complex environmental factors encountered in real world scenarios.<n>This paper introduces an environment-robust FSS setting that explicitly incorporates challenging test cases arising from complex environments.
• Score: 43.30169413561605
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• A New Dataset and Framework for Robust Road Surface Classification via Camera-IMU Fusion [3.571515153090507]
  Road surface classification (RSC) is a key enabler for environment-aware predictive maintenance systems.<n>Existing RSC techniques often fail to generalize beyond narrow operational conditions.<n>This work introduces a multimodal framework that fuses images and inertial measurements.
  arXiv  Detail & Related papers  (2026-01-28T18:46:29Z)
• DI3CL: Contrastive Learning With Dynamic Instances and Contour Consistency for SAR Land-Cover Classification Foundation Model [47.09803039926004]
  This paper develops a general-purpose foundation model for SAR land-cover classification.<n>It incorporates a Dynamic Instance and Contour Consistency Contrastive Learning (DI3CL) pre-training framework.<n>The results consistently demonstrate that the proposed DI3CL outperforms existing methods.
  arXiv  Detail & Related papers  (2025-11-11T03:58:22Z)
• Grounded Test-Time Adaptation for LLM Agents [75.62784644919803]
  Large language model (LLM)-based agents struggle to generalize to novel and complex environments.<n>We propose two strategies for adapting LLM agents by leveraging environment-specific information available during deployment.
  arXiv  Detail & Related papers  (2025-11-06T22:24:35Z)
• Data Augmentation and Resolution Enhancement using GANs and Diffusion Models for Tree Segmentation [49.13393683126712]
  Urban forests play a key role in enhancing environmental quality and supporting biodiversity in cities.<n> accurately detecting trees is challenging due to complex landscapes and the variability in image resolution caused by different satellite sensors or UAV flight altitudes.<n>We propose a novel pipeline that integrates domain adaptation with GANs and Diffusion models to enhance the quality of low-resolution aerial images.
  arXiv  Detail & Related papers  (2025-05-21T03:57:10Z)
• Open-set Anomaly Segmentation in Complex Scenarios [88.11076112792992]
  This paper introduces ComsAmy, a benchmark for open-set anomaly segmentation in complex scenarios.<n>ComsAmy encompasses a wide spectrum of adverse weather conditions, dynamic driving environments, and diverse anomaly types.<n>We propose a novel energy-entropy learning (EEL) strategy that integrates the complementary information from energy and entropy.
  arXiv  Detail & Related papers  (2025-04-28T12:00:10Z)
• Enhancing Environmental Robustness in Few-shot Learning via Conditional Representation Learning [27.549889991320203]
  Few-shot learning has been extensively utilized to overcome the scarcity of training data in domain-specific visual recognition.<n>In real-world scenarios, environmental factors such as complex backgrounds, varying lighting conditions, long-distance shooting, and moving targets often cause test images to exhibit numerous incomplete targets or noise disruptions.<n>We propose a novel conditional representation learning network (CRLNet) that integrates the interactions between training and testing images as conditional information in their respective representation processes.
  arXiv  Detail & Related papers  (2025-02-03T09:18:03Z)
• Enhancing Object Detection with Hybrid dataset in Manufacturing Environments: Comparing Federated Learning to Conventional Techniques [0.0]
  Federated Learning (FL) has garnered significant attention in manufacturing for its robust model development and privacy-preserving capabilities. This paper contributes to research focused on the robustness of FL models in object detection.
  arXiv  Detail & Related papers  (2024-08-16T18:50:06Z)
• MuLA-GAN: Multi-Level Attention GAN for Enhanced Underwater Visibility [1.9272863690919875]
  We introduce MuLA-GAN, a novel approach that leverages the synergistic power of Geneversarative Adrial Networks (GANs) and Multi-Level Attention mechanisms for comprehensive underwater image enhancement. Our model excels in capturing and preserving intricate details in underwater imagery, essential for various applications. This work not only addresses a significant research gap in underwater image enhancement but also underscores the pivotal role of Multi-Level Attention in enhancing GANs.
  arXiv  Detail & Related papers  (2023-12-25T07:33:47Z)
• Consistency Regularization for Generalizable Source-free Domain Adaptation [62.654883736925456]
  Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset. Existing SFDA methods ONLY assess their adapted models on the target training set, neglecting the data from unseen but identically distributed testing sets. We propose a consistency regularization framework to develop a more generalizable SFDA method.
  arXiv  Detail & Related papers  (2023-08-03T07:45:53Z)
• Salient Objects in Clutter [130.63976772770368]
  This paper identifies and addresses a serious design bias of existing salient object detection (SOD) datasets. This design bias has led to a saturation in performance for state-of-the-art SOD models when evaluated on existing datasets. We propose a new high-quality dataset and update the previous saliency benchmark.
  arXiv  Detail & Related papers  (2021-05-07T03:49:26Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.