Benchmarking Convolutional, Transformer, Hybrid, and Vision Language Models for Multi Disease Retinal Screening
This study benchmarks 12 architectures across four model families on the Retinal Fundus Multi-disease Image Dataset (RFMiD) for binary screening and multi-label classification. All models achieve AUC>84% in binary screening, with attention-based models (SwinTiny, CoAtNet0, MaxViTTiny) performing best. Vision-language models are competitive with CNNs but do not surpass top transformers and hybrids. External validation on Messidor-2 yields AUC 66.8%-84.7%, with hybrid and transformer models demonstrating strong performance.
Article intelligence
Key points
- Attention-based models (SwinTiny, CoAtNet0, MaxViTTiny) outperform others on RFMiD for multi-disease retinal screening.
- Vision-language models (e.g., CLIP ViT-B/16) are competitive with CNNs but not top transformers/hybrids.
- External validation shows hybrid and transformer models generalize well for diabetic retinopathy screening.
Why it matters
This matters because attention-based models (SwinTiny, CoAtNet0, MaxViTTiny) outperform others on RFMiD for multi-disease retinal screening.
Technical impact
May affect model selection, inference cost, product capability, and evaluation benchmarks.
[2605.26283] Benchmarking Convolutional, Transformer, Hybrid, and Vision Language Models for Multi Disease Retinal Screening
[Submitted on 25 May 2026]
Title:Benchmarking Convolutional, Transformer, Hybrid, and Vision Language Models for Multi Disease Retinal Screening
View a PDF of the paper titled Benchmarking Convolutional, Transformer, Hybrid, and Vision Language Models for Multi Disease Retinal Screening, by Durjoy Dey and 2 other authors
View PDF HTML (experimental)
Abstract:Modern deep learning offers powerful tools for automated retinal screening, but it remains unclear how different visual model families compare in realistic multi-disease settings and under domain shift. In this work, we benchmark twelve architectures across four model families: convolutional neural networks, vision transformers, hybrid CNN-transformer backbones, and vision-language models, using the Retinal Fundus Multi-disease Image Dataset (RFMiD). We evaluate two tasks: binary screening for any retinal disease and multi-label classification across 28 disease classes. Using standardized training, calibration, and evaluation protocols, we report AUC, F1, precision, recall, and sensitivity at a clinically relevant operating point with specificity near 80%. On RFMiD, all architectures perform well on binary screening, with AUC above 84%, but attention-based models perform best. SwinTiny and the hybrid CoAtNet0 and MaxViTTiny models achieve the strongest binary screening results and improve macro and micro F1 in the multi-label setting. Vision-language models, including CLIP ViT-B/16 and SigLIP-Base384, are competitive with CNN baselines but do not surpass the best transformer and hybrid backbones. In external validation on Messidor-2 for referable diabetic retinopathy, AUC ranges from 66.8% to 84.7%, with hybrid and transformer models again showing strong performance. These results provide a reproducible reference for model selection in multi-disease retinal screening and guide future automated screening tools for clinical deployment.
Comments: 12 pages, 3 figures, accepted at ICMHI 2026, 10th International Conference on Medical and Health Informatics, Kyoto, Japan. To appear in ACM Conference Proceedings
Subjects:
Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
Cite as: arXiv:2605.26283 [cs.CV]
(or arXiv:2605.26283v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2605.26283
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Durjoy Dey [view email] [v1] Mon, 25 May 2026 19:09:35 UTC (317 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Benchmarking Convolutional, Transformer, Hybrid, and Vision Language Models for Multi Disease Retinal Screening, by Durjoy Dey and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CV
new | recent | 2026-05
Change to browse by:
cs cs.LG
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)