FunOTTA: On-the-Fly Adaptation on Cross-Domain Fundus Image via Stable Test-time Training

• URL: http://arxiv.org/abs/2407.04396v3
• Date: Fri, 07 Nov 2025 03:28:59 GMT
• Title: FunOTTA: On-the-Fly Adaptation on Cross-Domain Fundus Image via Stable Test-time Training
• Authors: Qian Zeng, Le Zhang, Yipeng Liu, Ce Zhu, Fan Zhang,
• Abstract summary: We propose a novel Fundus On-the-fly Test-Time Adaptation (FunOTTA) framework that effectively generalizes a fundus image diagnosis model to unseen environments.<n>FunOTTA stands out for its stable adaptation process by performing dynamic disambiguation in the memory bank while minimizing harmful prior knowledge bias.<n> Experiments on cross-domain fundus image benchmarks across two diseases demonstrate the superiority of the overall framework.
• Score: 40.728092407170756
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fundus images are essential for the early screening and detection of eye diseases. While deep learning models using fundus images have significantly advanced the diagnosis of multiple eye diseases, variations in images from different imaging devices and locations (known as domain shifts) pose challenges for deploying pre-trained models in real-world applications. To address this, we propose a novel Fundus On-the-fly Test-Time Adaptation (FunOTTA) framework that effectively generalizes a fundus image diagnosis model to unseen environments, even under strong domain shifts. FunOTTA stands out for its stable adaptation process by performing dynamic disambiguation in the memory bank while minimizing harmful prior knowledge bias. We also introduce a new training objective during adaptation that enables the classifier to incrementally adapt to target patterns with reliable class conditional estimation and consistency regularization. We compare our method with several state-of-the-art test-time adaptation (TTA) pipelines. Experiments on cross-domain fundus image benchmarks across two diseases demonstrate the superiority of the overall framework and individual components under different backbone networks. Code is available at https://github.com/Casperqian/FunOTTA.

Related papers

• UOPSL: Unpaired OCT Predilection Sites Learning for Fundus Image Diagnosis Augmentation [47.08936359575974]
  We propose a novel unpaired multimodal framework UOPSL that utilizes extensive OCT-derived spatial priors to dynamically identify predilection sites.<n>Our approach bridges unpaired fundus and OCTs via extended disease text descriptions.<n>Experiments conducted on 9 diverse datasets across 28 critical categories demonstrate that our framework outperforms existing benchmarks.
  arXiv  Detail & Related papers  (2025-09-10T14:19:59Z)
• Enhancing Fundus Image-based Glaucoma Screening via Dynamic Global-Local Feature Integration [26.715346685730484]
  We propose a self-adaptive attention window that autonomously determines optimal boundaries for enhanced feature extraction. We also introduce a multi-head attention mechanism to effectively fuse global and local features via feature linear readout. Experimental results demonstrate that our method achieves superior accuracy and robustness in glaucoma classification.
  arXiv  Detail & Related papers  (2025-04-01T05:28:14Z)
• Test-Time Domain Generalization via Universe Learning: A Multi-Graph Matching Approach for Medical Image Segmentation [17.49123106322442]
  Test-time adaptation (TTA) adjusts a learned model using unlabeled test data.<n>We incorporate morphological information and propose a framework based on multi-graph matching.<n>Our method outperforms other state-of-the-art approaches on two medical image segmentation benchmarks.
  arXiv  Detail & Related papers  (2025-03-17T10:11:11Z)
• Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images [68.42215385041114]
  This paper introduces a novel lightweight multi-level adaptation and comparison framework to repurpose the CLIP model for medical anomaly detection. Our approach integrates multiple residual adapters into the pre-trained visual encoder, enabling a stepwise enhancement of visual features across different levels. Our experiments on medical anomaly detection benchmarks demonstrate that our method significantly surpasses current state-of-the-art models.
  arXiv  Detail & Related papers  (2024-03-19T09:28:19Z)
• Enhance Eye Disease Detection using Learnable Probabilistic Discrete Latents in Machine Learning Architectures [1.6000489723889526]
  Ocular diseases, including diabetic retinopathy and glaucoma, present a significant public health challenge. Deep learning models have emerged as powerful tools for analysing medical images, such as retina imaging. Challenges persist in model relibability and uncertainty estimation, which are critical for clinical decision-making.
  arXiv  Detail & Related papers  (2024-01-21T04:14:54Z)
• Affine-Consistent Transformer for Multi-Class Cell Nuclei Detection [76.11864242047074]
  We propose a novel Affine-Consistent Transformer (AC-Former), which directly yields a sequence of nucleus positions. We introduce an Adaptive Affine Transformer (AAT) module, which can automatically learn the key spatial transformations to warp original images for local network training. Experimental results demonstrate that the proposed method significantly outperforms existing state-of-the-art algorithms on various benchmarks.
  arXiv  Detail & Related papers  (2023-10-22T02:27:02Z)
• Generative Adversarial Networks for Stain Normalisation in Histopathology [2.2166690647926037]
  One of the significant roadblocks to current research is the high level of visual variability across digital pathology images. Sten normalisation aims to standardise the visual profile of digital pathology images without changing the structural content of the images. This is an ongoing field of study as researchers aim to identify a method which efficiently normalises pathology images to make AI models more robust and generalisable.
  arXiv  Detail & Related papers  (2023-08-05T11:38:05Z)
• 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)
• Forward-Forward Contrastive Learning [4.465144120325802]
  We propose Forward Forward Contrastive Learning (FFCL) as a novel pretraining approach for medical image classification. FFCL achieves superior performance (3.69% accuracy over ImageNet pretrained ResNet-18) over existing pretraining models in the pneumonia classification task.
  arXiv  Detail & Related papers  (2023-05-04T15:29:06Z)
• Domain-Specific Pre-training Improves Confidence in Whole Slide Image Classification [15.354256205808273]
  Whole Slide Images (WSIs) or histopathology images are used in digital pathology. WSIs pose great challenges to deep learning models for clinical diagnosis.
  arXiv  Detail & Related papers  (2023-02-20T08:42:06Z)
• DLTTA: Dynamic Learning Rate for Test-time Adaptation on Cross-domain Medical Images [56.72015587067494]
  We propose a novel dynamic learning rate adjustment method for test-time adaptation, called DLTTA. Our method achieves effective and fast test-time adaptation with consistent performance improvement over current state-of-the-art test-time adaptation methods.
  arXiv  Detail & Related papers  (2022-05-27T02:34:32Z)
• RADNet: Ensemble Model for Robust Glaucoma Classification in Color Fundus Images [0.0]
  Glaucoma is one of the most severe eye diseases, characterized by rapid progression and leading to irreversible blindness. Regular glaucoma screenings of the population shall improve early-stage detection, however the desirable frequency of etymological checkups is often not feasible. In our work, we propose an advanced image pre-processing technique combined with an ensemble of deep classification networks.
  arXiv  Detail & Related papers  (2022-05-25T16:48:00Z)
• On-the-Fly Test-time Adaptation for Medical Image Segmentation [63.476899335138164]
  Adapting the source model to target data distribution at test-time is an efficient solution for the data-shift problem. We propose a new framework called Adaptive UNet where each convolutional block is equipped with an adaptive batch normalization layer. During test-time, the model takes in just the new test image and generates a domain code to adapt the features of source model according to the test data.
  arXiv  Detail & Related papers  (2022-03-10T18:51:29Z)
• Assessing glaucoma in retinal fundus photographs using Deep Feature Consistent Variational Autoencoders [63.391402501241195]
  glaucoma is challenging to detect since it remains asymptomatic until the symptoms are severe. Early identification of glaucoma is generally made based on functional, structural, and clinical assessments. Deep learning methods have partially solved this dilemma by bypassing the marker identification stage and analyzing high-level information directly to classify the data.
  arXiv  Detail & Related papers  (2021-10-04T16:06:49Z)
• Self-Supervised Domain Adaptation for Diabetic Retinopathy Grading using Vessel Image Reconstruction [61.58601145792065]
  We learn invariant target-domain features by defining a novel self-supervised task based on retinal vessel image reconstructions. It can be shown that our approach outperforms existing domain strategies.
  arXiv  Detail & Related papers  (2021-07-20T09:44:07Z)
• Circumpapillary OCT-Focused Hybrid Learning for Glaucoma Grading Using Tailored Prototypical Neural Networks [1.1601676598120785]
  Glaucoma is one of the leading causes of blindness worldwide. We propose, for the first time, a novel framework for glaucoma grading using raw circumpapillary B-scans. In particular, we set out a new OCT-based hybrid network which combines hand-driven and deep learning algorithms.
  arXiv  Detail & Related papers  (2021-06-25T10:53:01Z)
• Automated Prostate Cancer Diagnosis Based on Gleason Grading Using Convolutional Neural Network [12.161266795282915]
  We propose a convolutional neural network (CNN)-based automatic classification method for accurate grading of prostate cancer (PCa) using whole slide histopathology images. A data augmentation method named Patch-Based Image Reconstruction (PBIR) was proposed to reduce the high resolution and increase the diversity of WSIs. A distribution correction module was developed to enhance the adaption of pretrained model to the target dataset.
  arXiv  Detail & Related papers  (2020-11-29T06:42:08Z)
• Leveraging Regular Fundus Images for Training UWF Fundus Diagnosis Models via Adversarial Learning and Pseudo-Labeling [29.009663623719064]
  Ultra-widefield (UWF) 200degreefundus imaging by Optos cameras has gradually been introduced. Regular fundus images contain a large amount of high-quality and well-annotated data. Due to the domain gap, models trained by regular fundus images to recognize UWF fundus images perform poorly. We propose the use of a modified cycle generative adversarial network (CycleGAN) model to bridge the gap between regular and UWF fundus.
  arXiv  Detail & Related papers  (2020-11-27T16:25:30Z)
• Modeling and Enhancing Low-quality Retinal Fundus Images [167.02325845822276]
  Low-quality fundus images increase uncertainty in clinical observation and lead to the risk of misdiagnosis. We propose a clinically oriented fundus enhancement network (cofe-Net) to suppress global degradation factors. Experiments on both synthetic and real images demonstrate that our algorithm effectively corrects low-quality fundus images without losing retinal details.
  arXiv  Detail & Related papers  (2020-05-12T08:01:16Z)

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.