Model-J SupViT
Collection
998 items • Updated
Model-J: SupViT Model (model_idx_0851)
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 | 9e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 851 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9904 |
| Val Accuracy | 0.9219 |
| Test Accuracy | 0.9174 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
possum, oak_tree, castle, couch, can, bottle, lamp, beaver, sea, skunk, plate, house, streetcar, cloud, mountain, pear, bed, crocodile, chair, tulip, road, clock, porcupine, pickup_truck, caterpillar, dolphin, rose, plain, bicycle, maple_tree, crab, leopard, mouse, cup, apple, bus, beetle, bowl, seal, girl, television, hamster, woman, ray, orange, cattle, willow_tree, table, lizard, squirrel
- Downloads last month
- 1
Model tree for ProbeX/Model-J__SupViT__model_idx_0851
Base model
google/vit-base-patch16-224