Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0658)
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 | val |
| Base Model | google/vit-base-patch16-224 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 5e-05 |
| LR Scheduler | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 658 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9904 |
| Val Accuracy | 0.9413 |
| Test Accuracy | 0.9388 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
hamster, bicycle, rabbit, forest, willow_tree, raccoon, possum, crocodile, mushroom, motorcycle, butterfly, trout, snake, dinosaur, mountain, chair, seal, ray, skyscraper, skunk, keyboard, streetcar, aquarium_fish, orange, tulip, girl, sweet_pepper, cloud, leopard, worm, wardrobe, woman, bottle, tank, bowl, beaver, mouse, cup, caterpillar, lamp, rose, oak_tree, snail, whale, chimpanzee, television, plain, table, otter, palm_tree
- Downloads last month
- 10
Model tree for ProbeX/Model-J__SupViT__model_idx_0658
Base model
google/vit-base-patch16-224