Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0579)
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 | 9e-05 |
| LR Scheduler | constant |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 579 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9918 |
| Val Accuracy | 0.9416 |
| Test Accuracy | 0.9360 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
orange, cockroach, lamp, elephant, beaver, bottle, dinosaur, pickup_truck, rabbit, lawn_mower, squirrel, lion, apple, whale, butterfly, couch, dolphin, willow_tree, chimpanzee, tiger, clock, possum, tulip, mushroom, streetcar, chair, man, rose, snake, cloud, table, sea, shrew, lobster, tractor, wardrobe, palm_tree, kangaroo, rocket, bed, can, trout, house, bus, porcupine, bee, raccoon, fox, orchid, leopard
- Downloads last month
- 1
Model tree for ProbeX/Model-J__SupViT__model_idx_0579
Base model
google/vit-base-patch16-224