Test-Time Degradation Adaptation for Open-Set Image Restoration
In contrast to close-set scenarios that restore images from a predefined set of degradations, open-set image restoration aims to handle the unknown degradations that were unforeseen during the pretraining phase, which is less-touched as far as we know. This work study this challenging problem and reveal its essence as unidentified distribution shifts between the test and training data. Recently, test-time adaptation has emerged as a fundamental method to address this inherent disparities. Inspired by it, we propose a test-time degradation adaptation framework for open-set image restoration, which consists of three components, \textit{i.e.}, i) a pre-trained and degradation-agnostic diffusion model for generating clean images, ii) a test-time degradation adapter adapts the unknown degradations based on the input image during the testing phase, and iii) the adapter-guided image restoration guides the model through the adapter to produce the corresponding clean image. Through experiments on multiple degradations, we show that our method achieves comparable even better performance than those task-specific methods. The code is available at https://github.com/XLearning-SCU/2024-ICML-TAO.
Code (0)
등록된 구현이 없습니다.
Tasks
Image RestorationTest-time AdaptationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction
Image super-resolution (SR) aims to learn a mapping from low-resolution (LR) to high-resolution (HR) using paired HR-LR training images. Conventional SR methods typically gather the paired training data by synthesizing L…
Image Super-ResolutionSuper-ResolutionTest-time AdaptationFrom Controlled Scenarios to Real-World: Cross-Domain Degradation Pattern Matching for All-in-One Image Restoration
As a fundamental imaging task, All-in-One Image Restoration (AiOIR) aims to achieve image restoration caused by multiple degradation patterns via a single model with unified parameters. Although existing AiOIR approaches…
AllContrastive LearningDomain AdaptationImage Restoration+1HyperTTA: Test-Time Adaptation for Hyperspectral Image Classification under Distribution Shifts
Hyperspectral image (HSI) classification models are highly sensitive to distribution shifts caused by real-world degradations such as noise, blur, compression, and atmospheric effects. To address this challenge, we propo…
Hyperspectral Image ClassificationTest-time AdaptationPISA: A Pseudo-Individual Source-Domain Feature Adaptation Framework for Test-Time Open-Vocabulary Object Detection
Open-vocabulary object detection test-time adaptation (OVOD-TTA) aims to address the performance degradation that pre-trained base models suffer when encountering image-domain shifts. Existing source-free OVOD-TTA method…
Test-time AdaptationObject DetectionA Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
Machine learning methods strive to acquire a robust model during the training process that can effectively generalize to test samples, even in the presence of distribution shifts. However, these methods often suffer from…
Domain AdaptationSource-Free Domain AdaptationSurveyTest-time Adaptation