Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0707)
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 | 3e-05 |
| LR Scheduler | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 707 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9967 |
| Val Accuracy | 0.9504 |
| Test Accuracy | 0.9530 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
can, sea, sunflower, raccoon, crocodile, wolf, woman, bear, tractor, cockroach, rocket, wardrobe, snail, tulip, keyboard, lawn_mower, flatfish, skyscraper, dolphin, train, plain, motorcycle, skunk, mountain, palm_tree, camel, orchid, lizard, house, beaver, castle, cloud, ray, rabbit, pickup_truck, snake, maple_tree, bus, dinosaur, lamp, hamster, man, shark, table, lion, mushroom, forest, mouse, worm, rose
- Downloads last month
- 2
Model tree for ProbeX/Model-J__SupViT__model_idx_0707
Base model
google/vit-base-patch16-224