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_0523)
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 | train |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0003 |
| LR Scheduler | constant |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 523 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9669 |
| Val Accuracy | 0.7880 |
| Test Accuracy | 0.7982 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mouse, sweet_pepper, orange, cattle, oak_tree, bus, palm_tree, rabbit, motorcycle, shrew, hamster, sunflower, spider, pear, beetle, baby, snail, can, elephant, sea, couch, lobster, lawn_mower, cup, man, lion, pickup_truck, bicycle, bed, caterpillar, flatfish, cockroach, trout, mountain, bee, bowl, castle, television, turtle, pine_tree, squirrel, lamp, telephone, chimpanzee, snake, streetcar, shark, lizard, willow_tree, cloud