Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0875)
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 | 0.0003 |
| LR Scheduler | constant |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 875 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9715 |
| Val Accuracy | 0.8715 |
| Test Accuracy | 0.8726 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
clock, sea, maple_tree, bowl, sweet_pepper, girl, porcupine, baby, table, bridge, snail, lawn_mower, elephant, bee, possum, skunk, bus, raccoon, lion, motorcycle, cup, aquarium_fish, dolphin, mushroom, shark, otter, boy, cloud, mouse, butterfly, tractor, spider, leopard, orange, beetle, trout, poppy, man, chimpanzee, hamster, oak_tree, plate, skyscraper, camel, bear, squirrel, bottle, keyboard, worm, lizard
- Downloads last month
- 2
Model tree for ProbeX/Model-J__SupViT__model_idx_0875
Base model
google/vit-base-patch16-224