Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0690)
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 | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 690 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9949 |
| Val Accuracy | 0.9461 |
| Test Accuracy | 0.9408 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
plate, tulip, castle, cattle, elephant, rocket, forest, tractor, apple, poppy, bowl, bicycle, spider, whale, possum, kangaroo, worm, bed, dolphin, wardrobe, clock, raccoon, butterfly, oak_tree, squirrel, motorcycle, road, crab, plain, fox, mushroom, crocodile, seal, mountain, mouse, snail, aquarium_fish, shrew, camel, train, streetcar, table, orange, caterpillar, chair, woman, lobster, couch, chimpanzee, beaver
- Downloads last month
- -
Model tree for ProbeX/Model-J__SupViT__model_idx_0690
Base model
google/vit-base-patch16-224