Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0705)
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 | 0.0001 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 705 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9998 |
| Val Accuracy | 0.9432 |
| Test Accuracy | 0.9476 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
flatfish, shark, seal, spider, hamster, streetcar, snake, boy, girl, plate, lizard, maple_tree, bottle, mountain, lamp, porcupine, dolphin, woman, bowl, cattle, clock, pear, fox, rabbit, motorcycle, otter, orange, pickup_truck, lawn_mower, mushroom, chimpanzee, tiger, sweet_pepper, tulip, apple, poppy, chair, couch, cup, crab, rose, train, kangaroo, telephone, skyscraper, bear, leopard, cockroach, crocodile, road
- Downloads last month
- 1
Model tree for ProbeX/Model-J__SupViT__model_idx_0705
Base model
google/vit-base-patch16-224