Unsupervised Adaptation of Polyp Segmentation Models via Coarse-to-Fine Self-Supervision

by   Jiexiang Wang, et al.

Unsupervised Domain Adaptation (UDA) has attracted a surge of interest over the past decade but is difficult to be used in real-world applications. Considering the privacy-preservation issues and security concerns, in this work, we study a practical problem of Source-Free Domain Adaptation (SFDA), which eliminates the reliance on annotated source data. Current SFDA methods focus on extracting domain knowledge from the source-trained model but neglects the intrinsic structure of the target domain. Moreover, they typically utilize pseudo labels for self-training in the target domain, but suffer from the notorious error accumulation problem. To address these issues, we propose a new SFDA framework, called Region-to-Pixel Adaptation Network (RPANet), which learns the region-level and pixel-level discriminative representations through coarse-to-fine self-supervision. The proposed RPANet consists of two modules, Foreground-aware Contrastive Learning (FCL) and Confidence-Calibrated Pseudo-Labeling (CCPL), which explicitly address the key challenges of “how to distinguish” and “how to refine”. To be specific, FCL introduces a supervised contrastive learning paradigm in the region level to contrast different region centroids across different target images, which efficiently involves all pseudo labels while robust to noisy samples. CCPL designs a novel fusion strategy to reduce the overconfidence problem of pseudo labels by fusing two different target predictions without introducing any additional network modules. Extensive experiments on three cross-domain polyp segmentation tasks reveal that RPANet significantly outperforms state-of-the-art SFDA and UDA methods without access to source data, revealing the potential of SFDA in medical applications.


page 4

page 8

page 9

page 10


Source-Free Domain Adaptive Fundus Image Segmentation with Denoised Pseudo-Labeling

Domain adaptation typically requires to access source domain data to uti...

Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data

Unsupervised domain adaptation aims to align a labeled source domain and...

Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic Segmentation

Unsupervised Domain Adaptation (UDA) of semantic segmentation transfers ...

ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain Adaptation

Large-scale Pre-Training Vision-Language Model such as CLIP has demonstr...

Contrastive Mean Teacher for Domain Adaptive Object Detectors

Object detectors often suffer from the domain gap between training (sour...

C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptation

Unsupervised domain adaptation (UDA) approaches focus on adapting models...

Confidence Attention and Generalization Enhanced Distillation for Continuous Video Domain Adaptation

Continuous Video Domain Adaptation (CVDA) is a scenario where a source m...

Please sign up or login with your details

Forgot password? Click here to reset