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_0591)
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_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 591 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9324 |
| Val Accuracy | 0.8384 |
| Test Accuracy | 0.8374 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tulip, snake, tractor, mushroom, orange, television, house, rocket, willow_tree, flatfish, caterpillar, trout, lizard, snail, shark, pine_tree, whale, bus, bowl, leopard, bridge, crocodile, shrew, butterfly, train, palm_tree, lobster, possum, chair, can, tiger, sea, cup, sweet_pepper, poppy, wardrobe, mountain, mouse, rabbit, motorcycle, otter, bear, clock, elephant, fox, baby, beetle, spider, streetcar, wolf