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_0652)
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 | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 652 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9669 |
| Val Accuracy | 0.8611 |
| Test Accuracy | 0.8612 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
woman, bowl, turtle, clock, tulip, camel, willow_tree, bicycle, sweet_pepper, elephant, hamster, fox, sea, poppy, raccoon, road, oak_tree, plate, bee, table, worm, kangaroo, bed, crocodile, flatfish, skunk, pine_tree, bridge, orange, tank, mushroom, dinosaur, chimpanzee, lamp, orchid, possum, bus, rabbit, bottle, spider, leopard, mountain, girl, rose, pear, maple_tree, snail, tiger, lawn_mower, streetcar