mlsanityData to 14 Oct 2026

Multi-style conversion for semantic segmentation of lesions in fundus images by adversarial attacks

arXiv 2410.13822 ↗First posted 17 Oct 2024cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

The diagnosis of diabetic retinopathy, which relies on fundus images, faces challenges in achieving transparency and interpretability when using a global classification approach. However, segmentation-based databases are significantly more expensive to acquire and combining them is often problematic. This paper introduces a novel method, termed adversarial style conversion, to address the lack of standardization in annotation styles across diverse databases. By training a single architecture on combined databases, the model spontaneously modifies its segmentation style depending on the input, demonstrating the ability to convert among different labeling styles. The proposed methodology adds a linear probe to detect dataset origin based on encoder features and employs adversarial attacks to condition the model's segmentation style. Results indicate significant qualitative and quantitative through dataset combination, offering avenues for improved model generalization, uncertainty estimation and continuous interpolation between annotation styles. Our approach enables training a segmentation model with diverse databases while controlling and leveraging annotation styles for improved retinopathy diagnosis.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 58 references that are in the map. First posted on arXiv 17 Oct 2024.

Builds on

28 of 58 references.

References · 28

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  6. 2017Squeeze-and-Excitation Networkscited by 4,789
  7. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  8. 2022A ConvNet for the 2020scited by 3,579
  9. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  10. 2016Wide Residual Networkscited by 3,070
  11. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  12. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,525
16 more
  1. 2016Understanding intermediate layers using linear classifier probescited by 1,353
  2. 2017Adversarial Discriminative Domain Adaptationcited by 1,311
  3. 2020ResNeSt: Split-Attention Networkscited by 445
  4. 2018A Probabilistic U-Net for Segmentation of Ambiguous Imagescited by 283
  5. 2020Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertaintycited by 101
  6. 2019Evaluation of Retinal Image Quality Assessment Networks in Different Color-spacescited by 57
  7. 2020A Benchmark for Studying Diabetic Retinopathy: Segmentation, Grading, and Transferabilitycited by 49
  8. 2019Learn to Segment Retinal Lesions and Beyondcited by 33
  9. 2018Feature Pyramid Network for Multi-Class Land Segmentationcited by 24
  10. 2022Proximal Splitting Adversarial Attacks for Semantic Segmentationcited by 23
  11. 2023That Label's Got Style: Handling Label Style Bias for Uncertain Image Segmentationcited by 13
  12. 2021Label noise in segmentation networks : mitigation must deal with biascited by 10
  13. 2019Learning Mutually Local-global U-nets For High-resolution Retinal Lesion Segmentation in Fundus Imagescited by 9
  14. 2023Effect of latent space distribution on the segmentation of images with multiple annotationscited by 7
  15. 2022Progressive Multi-scale Consistent Network for Multi-class Fundus Lesion Segmentationcited by 4
  16. 2023TJDR: A High-Quality Diabetic Retinopathy Pixel-Level Annotation Datasetcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Adversarial Vessel-Unveiling Semi-Supervised Segmentation for Retinopathy of Prematurity Diagnosis
  2. 2024Enhancing Diagnostic Accuracy in Rare and Common Fundus Diseases with a Knowledge-Rich Vision-Language Model
  3. 2026FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMs
  4. 2026From Pixels to Explanations: Interpretable Diabetic Retinopathy Grading with CNN-Transformer Ensembles, Visual Explainability and Vision-Language Models
  5. 2025RetinaLogos: Fine-Grained Synthesis of High-Resolution Retinal Images Through Captions
  6. 2024TP-DRSeg: Improving Diabetic Retinopathy Lesion Segmentation with Explicit Text-Prompts Assisted SAM
  7. 2024Exploring the Transferability of a Foundation Model for Fundus Images: Application to Hypertensive Retinopathy
  8. 2025Interpretable Few-Shot Retinal Disease Diagnosis with Concept-Guided Prompting of Vision-Language Models