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_0624)
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 | 0.0001 |
| LR Scheduler | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 624 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9664 |
| Val Accuracy | 0.8501 |
| Test Accuracy | 0.8400 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
possum, willow_tree, maple_tree, beaver, beetle, chair, seal, squirrel, woman, castle, forest, snake, motorcycle, couch, snail, tractor, elephant, caterpillar, man, baby, otter, television, shrew, poppy, worm, plain, wolf, turtle, lizard, camel, leopard, crocodile, lamp, skunk, plate, mountain, pine_tree, cup, bed, streetcar, flatfish, road, bowl, palm_tree, orange, pickup_truck, clock, aquarium_fish, bear, hamster