metadata
base_model: facebook/vit-mae-base
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: MAE Model (model_idx_0585)
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 | val |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 585 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9983 |
| Val Accuracy | 0.8725 |
| Test Accuracy | 0.8838 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
shrew, cattle, lobster, woman, cockroach, maple_tree, skunk, tulip, bear, train, mountain, chair, seal, orange, willow_tree, sea, spider, trout, forest, whale, bus, otter, man, mouse, telephone, lizard, lawn_mower, camel, streetcar, shark, castle, pine_tree, worm, beaver, cup, bicycle, crab, squirrel, bottle, house, elephant, tank, apple, rocket, bridge, beetle, boy, chimpanzee, wolf, ray