Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0837)
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 | 3e-05 |
| LR Scheduler | constant |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 837 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9815 |
| Val Accuracy | 0.9413 |
| Test Accuracy | 0.9394 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
camel, elephant, poppy, seal, butterfly, kangaroo, squirrel, rose, table, lamp, sweet_pepper, cup, bridge, mountain, mouse, forest, rabbit, shrew, spider, orchid, bed, sunflower, bee, can, tiger, chimpanzee, bus, plain, willow_tree, ray, beaver, raccoon, couch, tulip, aquarium_fish, wardrobe, beetle, oak_tree, mushroom, dinosaur, hamster, tractor, caterpillar, rocket, plate, shark, keyboard, apple, bear, snake
- Downloads last month
- 4
Model tree for ProbeX/Model-J__SupViT__model_idx_0837
Base model
google/vit-base-patch16-224