Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0435)
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 | MAE |
| Split | test |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0003 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 435 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 1.0000 |
| Val Accuracy | 0.8573 |
| Test Accuracy | 0.8552 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
squirrel, can, maple_tree, poppy, raccoon, streetcar, lizard, tractor, bus, beaver, pine_tree, cloud, willow_tree, rabbit, sunflower, spider, baby, man, chimpanzee, rocket, plain, crab, telephone, snail, bowl, train, mushroom, mouse, ray, skunk, sweet_pepper, sea, chair, whale, camel, bridge, cup, bottle, lion, table, bee, seal, lamp, clock, cockroach, tank, skyscraper, leopard, tiger, butterfly
- Downloads last month
- 1
Model tree for ProbeX/Model-J__MAE__model_idx_0435
Base model
facebook/vit-mae-base