Towards Interpretable Foundation Models for Retinal Fundus Images

• URL: http://arxiv.org/abs/2603.18846v1
• Date: Thu, 19 Mar 2026 12:48:23 GMT
• Title: Towards Interpretable Foundation Models for Retinal Fundus Images
• Abstract summary: We propose Dual-IFM, a foundation model that is interpretable-by-design in two ways.<n>First, it provides local interpretability for individual images through class evidence maps that are faithful to the decision-making process.<n>Second, it provides global interpretability for entire datasets through a 2D projection layer that allows for direct visualization of the model's representation space.
• Score: 4.6495938989652075
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Foundation models are used to extract transferable representations from large amounts of unlabeled data, typically via self-supervised learning (SSL). However, many of these models rely on architectures that offer limited interpretability, which is a critical issue in high-stakes domains such as medical imaging. We propose Dual-IFM, a foundation model that is interpretable-by-design in two ways: First, it provides local interpretability for individual images through class evidence maps that are faithful to the decision-making process. Second, it provides global interpretability for entire datasets through a 2D projection layer that allows for direct visualization of the model's representation space. We trained our model on over 800,000 color fundus photography from various sources to learn generalizable, interpretable representations for different downstream tasks. Our results show that our model reaches a performance range similar to that of state-of-the-art foundation models with up to $16\times$ the number of parameters, while providing interpretable predictions on out-of-distribution data. Our results suggest that large-scale SSL pretraining paired with inherent interpretability can lead to robust representations for retinal imaging.

Related papers

• Guess the Unified Model: How Much Can We Recover from Generated Images? [3.248768581088291]
  We examine separability across corruption, domains, and prompt languages using images generated by seven unified models.<n>We show that model attribution is highly feasible as our model achieves near-perfect accuracy with around 20K images per model.
  arXiv  Detail & Related papers  (2026-05-24T20:59:08Z)
• Comparing Computational Pathology Foundation Models using Representational Similarity Analysis [0.6660458629649825]
  We systematically analyze the representational spaces of six CPath foundation models using techniques in computational neuroscience.<n>We find that UNI2 and Virchow2 have the most distinct representational structures, whereas Prov-Gigapath has the highest average similarity across models.
  arXiv  Detail & Related papers  (2025-09-18T23:01:13Z)
• UniVG: A Generalist Diffusion Model for Unified Image Generation and Editing [59.590505989071175]
  Text-to-Image (T2I) diffusion models have shown impressive results in generating visually compelling images following user prompts.<n>We introduce UniVG, a generalist diffusion model capable of supporting a diverse range of image generation tasks with a single set of weights.
  arXiv  Detail & Related papers  (2025-03-16T21:11:25Z)
• Multi-Scale and Multimodal Species Distribution Modeling [4.022195138381868]
  Species distribution models (SDMs) aim to predict the distribution of species relating occurrence data with environmental variables. Recent applications of deep learning to SDMs have enabled new avenues, specifically the inclusion of spatial data. We develop a modular structure for SDMs that allows us to test the effect of scale in both single- and multi-scale settings. Results on the GeoLifeCLEF 2023 benchmark indicate that considering multimodal data and learning multi-scale representations leads to more accurate models.
  arXiv  Detail & Related papers  (2024-11-06T15:57:20Z)
• DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception [66.88792390480343]
  We propose DEEM, a simple but effective approach that utilizes the generative feedback of diffusion models to align the semantic distributions of the image encoder.<n>DEEM exhibits enhanced robustness and a superior capacity to alleviate model hallucinations while utilizing fewer trainable parameters, less pre-training data, and a smaller base model size.
  arXiv  Detail & Related papers  (2024-05-24T05:46:04Z)
• FreeSeg-Diff: Training-Free Open-Vocabulary Segmentation with Diffusion Models [49.80911683739506]
  We focus on the task of image segmentation, which is traditionally solved by training models on closed-vocabulary datasets.<n>We leverage different and relatively small-sized, open-source foundation models for zero-shot open-vocabulary segmentation.<n>Our approach (dubbed FreeSeg-Diff), which does not rely on any training, outperforms many training-based approaches on both Pascal VOC and COCO datasets.
  arXiv  Detail & Related papers  (2024-03-29T10:38:25Z)
• What Matters When Repurposing Diffusion Models for General Dense Perception Tasks? [49.84679952948808]
  Recent works show promising results by simply fine-tuning T2I diffusion models for dense perception tasks.<n>We conduct a thorough investigation into critical factors that affect transfer efficiency and performance when using diffusion priors.<n>Our work culminates in the development of GenPercept, an effective deterministic one-step fine-tuning paradigm tailed for dense visual perception tasks.
  arXiv  Detail & Related papers  (2024-03-10T04:23:24Z)
• Learned representation-guided diffusion models for large-image generation [58.192263311786824]
  We introduce a novel approach that trains diffusion models conditioned on embeddings from self-supervised learning (SSL) Our diffusion models successfully project these features back to high-quality histopathology and remote sensing images. Augmenting real data by generating variations of real images improves downstream accuracy for patch-level and larger, image-scale classification tasks.
  arXiv  Detail & Related papers  (2023-12-12T14:45:45Z)
• Sequential Modeling Enables Scalable Learning for Large Vision Models [120.91839619284431]
  We introduce a novel sequential modeling approach which enables learning a Large Vision Model (LVM) without making use of any linguistic data. We define a common format, "visual sentences", in which we can represent raw images and videos as well as annotated data sources.
  arXiv  Detail & Related papers  (2023-12-01T18:59:57Z)
• UniDiff: Advancing Vision-Language Models with Generative and Discriminative Learning [86.91893533388628]
  This paper presents UniDiff, a unified multi-modal model that integrates image-text contrastive learning (ITC), text-conditioned image synthesis learning (IS), and reciprocal semantic consistency modeling (RSC) UniDiff demonstrates versatility in both multi-modal understanding and generative tasks.
  arXiv  Detail & Related papers  (2023-06-01T15:39:38Z)
• IMACS: Image Model Attribution Comparison Summaries [16.80986701058596]
  We introduce IMACS, a method that combines gradient-based model attributions with aggregation and visualization techniques. IMACS extracts salient input features from an evaluation dataset, clusters them based on similarity, then visualizes differences in model attributions for similar input features. We show how our technique can uncover behavioral differences caused by domain shift between two models trained on satellite images.
  arXiv  Detail & Related papers  (2022-01-26T21:35:14Z)

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.