RADAR weights

Trained read-out heads for RADAR (MICCAI 2026 TREAT-MMTB Task 2). Code and usage: adinathdukre/radar-tb.

The frozen encoder is microsoft/rad-dino; these files contain only the heads.

files	group
`dep_plain_seed{42,1337,2024}.pt`, `dep_aug_seed{42,1337,2024}.pt`	CR-slice heads, plain and style-randomized
`adv_seed{42,1337,2024}.pt`	modality-adversarial heads
`cdan_seed{42,1337,2024}.pt`	conditional-adversarial heads
`hires_seed{42,1337,2024}.pt`	700 px adversarial heads
`polarity_ref.npy`	reference embedding for inverted-export detection

python scripts/prepare.py --weights-repo adidukre/radar-tb
python scripts/predict.py --input /path/to/images --output /path/to/output

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support