gradeeye/seg-unet-tversky
Image Segmentation • Updated • 8
AI & ML interests
Diabetic retinopathy grading, domain generalization, ordinal regression, model calibration, medical imaging
Recent Activity
Organization Card
GradEye
Model checkpoints and code supporting our study on per-threshold calibration under domain shift in diabetic retinopathy (DR) grading. We use a CORN ordinal regression head across a leave-one-domain-out (LODO) protocol on four public fundus photograph datasets, and show that calibration — not just accuracy — degrades non-uniformly across ordinal thresholds under domain shift.
🔗 Paper: coming soon 🔗 Code: github.com/yourname/gradeeye 📄 License: see below (per-repo, not MIT — derived from restricted-use source data)
What we publish
Pretrained CNN/ViT backbones (ConvNeXt-Tiny, DeiT-3 Small/384, MaxViT-Tiny/384) with a CORN ordinal regression head, trained under a strict LODO protocol across four DR fundus photograph domains, plus auxiliary-channel variants (learned segmentation masks, Sobel edge maps) and the U-Net segmentation models used to generate them.
Data sources (LODO folds)
| Domain | Role |
|---|---|
| EyePACS | held-out fold / testing source |
| APTOS | held-out fold / testing source |
| Messidor-2 | held-out fold / testing source |
| DDR | held-out fold / testing source |
Each model is trained on 3 of the 4 domains and evaluated on the 4th, held-out domain — the model never sees that domain during training or model selection.
Key findings
| # | Finding | Headline number |
|---|---|---|
| 1 | Per-threshold calibration diverges structurally under domain shift | ECE range 0.05–0.29 across thresholds (6× spread on Messidor-2) |
| 2 | Post-hoc temperature scaling fails under shift — and fails the opposite way expected | T saturates at upper bound (5.0); model is under-confident, not overconfident |
| 3 | Class balancing hurts cross-domain accuracy in this LODO setup | unbalanced beats balanced by +3.93% mean QWK |
| 4 | Mild NPDR (grade 1) is the dominant cross-study failure mode | F1 < 0.13 on every fold, every variant |
| 5 | Best cross-domain backbone (of 3 tested) | ConvNeXt-Tiny, mean QWK 0.686 ± 0.156 |
Full per-fold, per-variant tables are in the paper and in each repo's model card.
Repository structure
One repo per training configuration (backbone × channel variant × loss). See the [Collection] (link once live) for the full index. Each repo's model card documents architecture, LODO fold, training hyperparameters, and metrics for that specific checkpoint set.
License
Model weights are derived from datasets with non-commercial,
research/academic-use restrictions (EyePACS and APTOS Kaggle competition
terms prohibit redistribution and commercial use). Accordingly, all
checkpoints in this org are released under cc-by-nc-4.0, research use
only. See each repo's card for source-dataset attribution. Raw source
images are not redistributed — only trained model weights.
Status
This is an active research project; some tables in the paper are still being finalized (confidence intervals, seed sensitivity, full ablation matrix). Findings above are from completed runs and are stable; exact numbers may be refined before camera-ready.
Author
[Ahmed Farhanur Rashid] · GitHub
models 7
gradeeye/seg-unet-bcedice
Image Segmentation • Updated • 10
gradeeye/four-ch-tversky
Image Classification • Updated • 11
gradeeye/four-ch-soft
Image Classification • Updated • 10
gradeeye/four-ch-morph
Image Classification • Updated • 10
gradeeye/baseline-3ch-unbalanced
Image Classification • Updated
gradeeye/baseline-3ch
Image Classification • Updated
datasets 0
None public yet