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_0513)
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 | 0.0005 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 513 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6036 |
| Val Accuracy | 0.5040 |
| Test Accuracy | 0.5042 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bottle, tulip, turtle, apple, pear, maple_tree, chimpanzee, can, bus, crab, couch, poppy, willow_tree, bowl, caterpillar, butterfly, cloud, road, crocodile, beetle, castle, palm_tree, orchid, wolf, plain, mouse, skunk, leopard, trout, table, snail, forest, rabbit, worm, lawn_mower, otter, camel, lizard, flatfish, snake, oak_tree, shrew, dolphin, skyscraper, ray, tank, boy, sunflower, bed, fox