SSL-DG: Rethinking and Fusing Semi-supervised Learning and Domain Generalization in Medical Image Segmentation

• URL: http://arxiv.org/abs/2311.02583v1
• Date: Sun, 5 Nov 2023 07:44:40 GMT
• Title: SSL-DG: Rethinking and Fusing Semi-supervised Learning and Domain Generalization in Medical Image Segmentation
• Authors: Zanting Ye
• Abstract summary: We show that unseen target data can be represented by a linear combination of source data, which can be achieved by simple data augmentation. We propose SSL-DG, fusing DG and SSL, to achieve cross-domain generalization with limited annotations.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep learning-based medical image segmentation is an essential yet challenging task in clinical practice, which arises from restricted access to annotated data coupled with the occurrence of domain shifts. Previous attempts have focused on isolated solutions, while disregarding their inter-connectedness. In this paper, we rethink the relationship between semi-supervised learning (SSL) and domain generalization (DG), which are the cutting-edge approaches to address the annotated data-driven constraints and the domain shift issues. Inspired by class-level representation, we show that unseen target data can be represented by a linear combination of source data, which can be achieved by simple data augmentation. The augmented data enrich domain distributions while having semantic consistency, aligning with the principles of consistency-based SSL. Accordingly, we propose SSL-DG, fusing DG and SSL, to achieve cross-domain generalization with limited annotations. Specifically, the global and focal region augmentation, together with an augmentation scale-balancing mechanism, are used to construct a mask-based domain diffusion augmentation module to significantly enrich domain diversity. In order to obtain consistent predictions for the same source data in different networks, we use uncertainty estimation and a deep mutual learning strategy to enforce the consistent constraint. Extensive experiments including ablation studies are designed to validate the proposed SSL-DG. The results demonstrate that our SSL-DG significantly outperforms state-of-the-art solutions in two challenging DG tasks with limited annotations. Code is available at https://github.com/yezanting/SSL-DG.

Related papers

• Domain-Guided Weight Modulation for Semi-Supervised Domain Generalization [11.392783918495404]
  We study the challenging problem of semi-supervised domain generalization. The goal is to learn a domain-generalizable model while using only a small fraction of labeled data and a relatively large fraction of unlabeled data. We propose a novel method that can facilitate the generation of accurate pseudo-labels under various domain shifts.
  arXiv  Detail & Related papers  (2024-09-04T01:26:23Z)
• Towards Generalizing to Unseen Domains with Few Labels [7.002657345547741]
  We aim to obtain a model that learns domain-generalizable features by leveraging a limited subset of labelled data. Existing domain generalization (DG) methods which are unable to exploit unlabeled data perform poorly compared to semi-supervised learning (SSL) methods.
  arXiv  Detail & Related papers  (2024-03-18T11:21:52Z)
• Towards Generic Semi-Supervised Framework for Volumetric Medical Image Segmentation [19.09640071505051]
  We develop a generic SSL framework to handle settings such as UDA and SemiDG. We evaluate our proposed framework on four benchmark datasets for SSL, Class-imbalanced SSL, UDA and SemiDG. The results showcase notable improvements compared to state-of-the-art methods across all four settings.
  arXiv  Detail & Related papers  (2023-10-17T14:58:18Z)
• Towards domain-invariant Self-Supervised Learning with Batch Styles Standardization [1.6060199783864477]
  Batch Styles Standardization (BSS) is a simple yet powerful method to standardize the style of images in a batch. We show that BSS significantly improves downstream task performances on unseen domains, often outperforming or rivaling UDG methods.
  arXiv  Detail & Related papers  (2023-03-10T17:09:04Z)
• Generalized Semantic Segmentation by Self-Supervised Source Domain Projection and Multi-Level Contrastive Learning [79.0660895390689]
  Deep networks trained on the source domain show degraded performance when tested on unseen target domain data. We propose a Domain Projection and Contrastive Learning (DPCL) approach for generalized semantic segmentation.
  arXiv  Detail & Related papers  (2023-03-03T13:07:14Z)
• Collaborative Intelligence Orchestration: Inconsistency-Based Fusion of Semi-Supervised Learning and Active Learning [60.26659373318915]
  Active learning (AL) and semi-supervised learning (SSL) are two effective, but often isolated, means to alleviate the data-hungry problem. We propose an innovative Inconsistency-based virtual aDvErial algorithm to further investigate SSL-AL's potential superiority. Two real-world case studies visualize the practical industrial value of applying and deploying the proposed data sampling algorithm.
  arXiv  Detail & Related papers  (2022-06-07T13:28:43Z)
• Transferrable Contrastive Learning for Visual Domain Adaptation [108.98041306507372]
  Transferrable Contrastive Learning (TCL) is a self-supervised learning paradigm tailored for domain adaptation. TCL penalizes cross-domain intra-class domain discrepancy between source and target through a clean and novel contrastive loss. The free lunch is, thanks to the incorporation of contrastive learning, TCL relies on a moving-averaged key encoder that naturally achieves a temporally ensembled version of pseudo labels for target data.
  arXiv  Detail & Related papers  (2021-12-14T16:23:01Z)
• Semi-supervised Domain Adaptive Structure Learning [72.01544419893628]
  Semi-supervised domain adaptation (SSDA) is a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. We introduce an adaptive structure learning method to regularize the cooperation of SSL and DA.
  arXiv  Detail & Related papers  (2021-12-12T06:11:16Z)
• FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space [63.43592895652803]
  Federated learning allows distributed medical institutions to collaboratively learn a shared prediction model with privacy protection. While at clinical deployment, the models trained in federated learning can still suffer from performance drop when applied to completely unseen hospitals outside the federation. We present a novel approach, named as Episodic Learning in Continuous Frequency Space (ELCFS), for this problem. The effectiveness of our method is demonstrated with superior performance over state-of-the-arts and in-depth ablation experiments on two medical image segmentation tasks.
  arXiv  Detail & Related papers  (2021-03-10T13:05:23Z)
• Towards Recognizing Unseen Categories in Unseen Domains [74.29101415077523]
  CuMix is a holistic algorithm to tackle Zero-Shot Learning (ZSL), Domain Adaptation and Domain Generalization (DG) and ZSL+DG. The key idea of CuMix is to simulate the test-time domain and semantic shift using images and features from unseen domains and categories available during training. Results on standard SL and DG datasets and on ZSL+DG using the DomainNet benchmark demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-07-23T21:09:28Z)

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.