Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0701)
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 | 0.0005 |
| LR Scheduler | constant_with_warmup |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 701 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9674 |
| Val Accuracy | 0.8515 |
| Test Accuracy | 0.8500 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tank, couch, mountain, beaver, pine_tree, can, telephone, rocket, cloud, snail, raccoon, skyscraper, television, shrew, cup, hamster, flatfish, rabbit, road, mouse, clock, orange, sea, tractor, skunk, dinosaur, crocodile, trout, lawn_mower, bus, pear, bee, motorcycle, forest, orchid, bridge, whale, possum, bottle, keyboard, aquarium_fish, elephant, oak_tree, fox, squirrel, girl, beetle, wolf, dolphin, poppy
- Downloads last month
- 3
Model tree for ProbeX/Model-J__SupViT__model_idx_0701
Base model
google/vit-base-patch16-224