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_0645)
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 | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 645 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9819 |
| Val Accuracy | 0.8675 |
| Test Accuracy | 0.8654 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
seal, porcupine, bowl, tiger, otter, television, bicycle, girl, palm_tree, dolphin, spider, poppy, leopard, castle, willow_tree, bee, skyscraper, skunk, rocket, orchid, elephant, lizard, train, lobster, house, forest, chair, chimpanzee, motorcycle, couch, keyboard, baby, ray, raccoon, snail, wardrobe, lawn_mower, butterfly, beaver, plain, kangaroo, man, tulip, lamp, aquarium_fish, clock, mushroom, bridge, maple_tree, cloud