# Domain Adaptive Diabetic Retinopathy Grading with Model Absence and Flowing Data

arXiv: https://arxiv.org/abs/2412.01203 · HTML: https://mlsanity.com/paper/2412.01203/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 41 references that are in the map.
- First posted on arXiv 2 Dec 2024.

## Builds on (most cited first, 21 of 21)

- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [See through Gradients: Image Batch Recovery via GradInversion](https://mlsanity.com/paper/2104.07586/) (2021)
- [Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation](https://mlsanity.com/paper/2110.04202/) (2021)
- [CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2109.06165/) (2021)
- [An introduction to domain adaptation and transfer learning](https://mlsanity.com/paper/1812.11806/) (2018)
- [Applications of Deep Learning in Fundus Images: A Review](https://mlsanity.com/paper/2101.09864/) (2021)
- [Confidence Score for Source-Free Unsupervised Domain Adaptation](https://mlsanity.com/paper/2206.06640/) (2022)
- [Unadversarial Examples: Designing Objects for Robust Vision](https://mlsanity.com/paper/2012.12235/) (2020)
- [On-the-Fly Test-time Adaptation for Medical Image Segmentation](https://mlsanity.com/paper/2203.05574/) (2022)
- [Towards Generalizable Diabetic Retinopathy Grading in Unseen Domains](https://mlsanity.com/paper/2307.04378/) (2023)
- [SSiT: Saliency-guided Self-supervised Image Transformer for Diabetic Retinopathy Grading](https://mlsanity.com/paper/2210.10969/) (2022)
- [Self-Supervised Domain Adaptation for Diabetic Retinopathy Grading using Vessel Image Reconstruction](https://mlsanity.com/paper/2107.09372/) (2021)
- [Unified Source-Free Domain Adaptation](https://mlsanity.com/paper/2403.07601/) (2024)
- [CAT:Collaborative Adversarial Training](https://mlsanity.com/paper/2303.14922/) (2023)
- [NSA: Naturalistic Support Artifact to Boost Network Confidence](https://mlsanity.com/paper/2307.14917/) (2023)
- [Saliency-guided and Patch-based Mixup for Long-tailed Skin Cancer Image Classification](https://mlsanity.com/paper/2406.10801/) (2024)

## Built on by (most cited first, 1 of 1)

- [3rd Place Solution to Human Motion Challenges in Real-World and Clinical Settings (MoCha) @ECCV2026: Language-Aligned Motion Representations for Domain-Generalizable UPDRS-Gait Severity Estimation](https://mlsanity.com/paper/2609.10187/) (2026)

## Abstract (arXiv)

Domain shift (the difference between source and target domains) poses a significant challenge in clinical applications, e.g., Diabetic Retinopathy (DR) grading. Despite considering certain clinical requirements, like source data privacy, conventional transfer methods are predominantly model-centered and often struggle to prevent model-targeted attacks. In this paper, we address a challenging Online Model-aGnostic Domain Adaptation (OMG-DA) setting, driven by the demands of clinical environments. This setting is characterized by the absence of the model and the flow of target data. To tackle the new challenge, we propose a novel approach, Generative Unadversarial ExampleS (GUES), which enables adaptation from a data-centric perspective. Specifically, we first theoretically reformulate conventional perturbation optimization in a generative way--learning a perturbation generation function with a latent input variable. During model instantiation, we leverage a Variational AutoEncoder to express this function. The encoder with the reparameterization trick predicts the latent input, whilst the decoder is responsible for the generation. Furthermore, the saliency map is selected as pseudo-perturbation labels. Because it not only captures potential lesions but also theoretically provides an upper bound on the function input, enabling the identification of the latent variable. Extensive comparative experiments on DR benchmarks with both frozen pre-trained models and trainable models demonstrate the superiority of GUES, showing robustness even with small batch size.