Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0987)
This model is part of the Model-J dataset, introduced in:
Learning on Model Weights using Tree Experts (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | SupViT |
| Split | train |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 987 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9408 |
| Val Accuracy | 0.8800 |
| Test Accuracy | 0.8686 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
porcupine, otter, sweet_pepper, snake, tiger, bridge, castle, keyboard, bicycle, squirrel, lion, couch, lawn_mower, dolphin, bus, tulip, chimpanzee, road, crab, bottle, telephone, train, cattle, dinosaur, lizard, wolf, butterfly, clock, woman, maple_tree, cup, worm, sea, chair, possum, lamp, tractor, streetcar, wardrobe, can, mountain, man, aquarium_fish, oak_tree, trout, skyscraper, raccoon, plain, baby, shrew
- Downloads last month
- 1
Model tree for ProbeX/Model-J__SupViT__model_idx_0987
Base model
google/vit-base-patch16-224