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_0590)
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 | linear |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 590 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9827 |
| Val Accuracy | 0.8731 |
| Test Accuracy | 0.8698 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lawn_mower, can, kangaroo, lobster, ray, sunflower, crab, baby, tank, chair, bee, cockroach, wardrobe, television, keyboard, seal, bottle, train, flatfish, wolf, snail, mouse, snake, table, woman, caterpillar, maple_tree, butterfly, rose, dolphin, rocket, mountain, dinosaur, aquarium_fish, squirrel, fox, beaver, bear, mushroom, leopard, pear, lizard, man, chimpanzee, telephone, tractor, castle, shrew, willow_tree, house