Distill-SODA: Distilling Self-Supervised Vision Transformer for Source-Free Open-Set Domain Adaptation in Computational Pathology

• URL: http://arxiv.org/abs/2307.04596v3
• Date: Tue, 16 Jan 2024 12:31:03 GMT
• Title: Distill-SODA: Distilling Self-Supervised Vision Transformer for Source-Free Open-Set Domain Adaptation in Computational Pathology
• Authors: Guillaume Vray, Devavrat Tomar, Jean-Philippe Thiran, Behzad Bozorgtabar
• Abstract summary: Development of computational pathology models is essential for reducing manual tissue typing from whole slide images. We propose a practical setting by addressing the above-mentioned challenges in one fell swoop, i.e., source-free open-set domain adaptation. Our methodology focuses on adapting a pre-trained source model to an unlabeled target dataset.
• Score: 12.828728138651266
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Developing computational pathology models is essential for reducing manual tissue typing from whole slide images, transferring knowledge from the source domain to an unlabeled, shifted target domain, and identifying unseen categories. We propose a practical setting by addressing the above-mentioned challenges in one fell swoop, i.e., source-free open-set domain adaptation. Our methodology focuses on adapting a pre-trained source model to an unlabeled target dataset and encompasses both closed-set and open-set classes. Beyond addressing the semantic shift of unknown classes, our framework also deals with a covariate shift, which manifests as variations in color appearance between source and target tissue samples. Our method hinges on distilling knowledge from a self-supervised vision transformer (ViT), drawing guidance from either robustly pre-trained transformer models or histopathology datasets, including those from the target domain. In pursuit of this, we introduce a novel style-based adversarial data augmentation, serving as hard positives for self-training a ViT, resulting in highly contextualized embeddings. Following this, we cluster semantically akin target images, with the source model offering weak pseudo-labels, albeit with uncertain confidence. To enhance this process, we present the closed-set affinity score (CSAS), aiming to correct the confidence levels of these pseudo-labels and to calculate weighted class prototypes within the contextualized embedding space. Our approach establishes itself as state-of-the-art across three public histopathological datasets for colorectal cancer assessment. Notably, our self-training method seamlessly integrates with open-set detection methods, resulting in enhanced performance in both closed-set and open-set recognition tasks.

Related papers

• Domain Adaptation for Medical Image Segmentation using Transformation-Invariant Self-Training [7.738197566031678]
  We propose a semi-supervised learning strategy for domain adaptation termed transformation-invariant self-training (TI-ST) The proposed method assesses pixel-wise pseudo-labels' reliability and filters out unreliable detections during self-training.
  arXiv  Detail & Related papers  (2023-07-31T13:42:56Z)
• Self-Paced Learning for Open-Set Domain Adaptation [50.620824701934]
  Traditional domain adaptation methods presume that the classes in the source and target domains are identical. Open-set domain adaptation (OSDA) addresses this limitation by allowing previously unseen classes in the target domain. We propose a novel framework based on self-paced learning to distinguish common and unknown class samples.
  arXiv  Detail & Related papers  (2023-03-10T14:11:09Z)
• A self-training framework for glaucoma grading in OCT B-scans [6.382852973055393]
  We present a self-training-based framework for glaucoma grading using OCT B-scans under the presence of domain shift. A two-step learning methodology resorts to pseudo-labels generated during the first step to augment the training dataset on the target domain. We propose a novel glaucoma-specific backbone which introduces residual and attention modules via skip-connections to refine the embedding features of the latent space.
  arXiv  Detail & Related papers  (2021-11-23T10:33:55Z)
• Source-Free Domain Adaptive Fundus Image Segmentation with Denoised Pseudo-Labeling [56.98020855107174]
  Domain adaptation typically requires to access source domain data to utilize their distribution information for domain alignment with the target data. In many real-world scenarios, the source data may not be accessible during the model adaptation in the target domain due to privacy issue. We present a novel denoised pseudo-labeling method for this problem, which effectively makes use of the source model and unlabeled target data.
  arXiv  Detail & Related papers  (2021-09-19T06:38:21Z)
• Generative Self-training for Cross-domain Unsupervised Tagged-to-Cine MRI Synthesis [10.636015177721635]
  We propose a novel generative self-training framework with continuous value prediction and regression objective for cross-domain image synthesis. Specifically, we propose to filter the pseudo-label with an uncertainty mask, and quantify the predictive confidence of generated images with practical variational Bayes learning.
  arXiv  Detail & Related papers  (2021-06-23T16:19:00Z)
• A Curriculum-style Self-training Approach for Source-Free Semantic Segmentation [91.13472029666312]
  We propose a curriculum-style self-training approach for source-free domain adaptive semantic segmentation. Our method yields state-of-the-art performance on source-free semantic segmentation tasks for both synthetic-to-real and adverse conditions.
  arXiv  Detail & Related papers  (2021-06-22T10:21:39Z)
• Source-Free Open Compound Domain Adaptation in Semantic Segmentation [99.82890571842603]
  In SF-OCDA, only the source pre-trained model and the target data are available to learn the target model. We propose the Cross-Patch Style Swap (CPSS) to diversify samples with various patch styles in the feature-level. Our method produces state-of-the-art results on the C-Driving dataset.
  arXiv  Detail & Related papers  (2021-06-07T08:38:41Z)
• TraND: Transferable Neighborhood Discovery for Unsupervised Cross-domain Gait Recognition [77.77786072373942]
  This paper proposes a Transferable Neighborhood Discovery (TraND) framework to bridge the domain gap for unsupervised cross-domain gait recognition. We design an end-to-end trainable approach to automatically discover the confident neighborhoods of unlabeled samples in the latent space. Our method achieves state-of-the-art results on two public datasets, i.e., CASIA-B and OU-LP.
  arXiv  Detail & Related papers  (2021-02-09T03:07:07Z)
• Progressive Graph Learning for Open-Set Domain Adaptation [48.758366879597965]
  Domain shift is a fundamental problem in visual recognition which typically arises when the source and target data follow different distributions. In this paper, we tackle a more realistic problem of open-set domain shift where the target data contains additional classes that are not present in the source data. We introduce an end-to-end Progressive Graph Learning framework where a graph neural network with episodic training is integrated to suppress underlying conditional shift.
  arXiv  Detail & Related papers  (2020-06-22T09:10:34Z)

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.