Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0408)
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 | 5e-05 |
| LR Scheduler | linear |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 408 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9976 |
| Val Accuracy | 0.9573 |
| Test Accuracy | 0.9562 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
wolf, can, keyboard, road, poppy, skyscraper, beaver, aquarium_fish, porcupine, trout, crab, dinosaur, house, bee, baby, shrew, caterpillar, bottle, ray, lamp, mushroom, skunk, tractor, bus, lawn_mower, snake, mouse, bridge, clock, hamster, rocket, plate, worm, spider, oak_tree, man, woman, raccoon, tank, fox, sea, chimpanzee, bowl, turtle, snail, crocodile, pear, butterfly, possum, rose
- Downloads last month
- 7
Model tree for ProbeX/Model-J__SupViT__model_idx_0408
Base model
google/vit-base-patch16-224