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_0161)
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 | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 161 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7753 |
| Val Accuracy | 0.5163 |
| Test Accuracy | 0.5276 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
raccoon, dolphin, bottle, lawn_mower, orange, cattle, snail, beetle, lobster, bicycle, pine_tree, caterpillar, hamster, sweet_pepper, castle, porcupine, can, skyscraper, rabbit, shark, kangaroo, maple_tree, whale, turtle, mountain, lion, palm_tree, tank, forest, elephant, mushroom, crab, chimpanzee, bus, shrew, television, wolf, streetcar, otter, pear, table, leopard, keyboard, rose, chair, wardrobe, train, lizard, camel, boy