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_0640)
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 | 3e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 640 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9611 |
| Val Accuracy | 0.8875 |
| Test Accuracy | 0.8832 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
house, beaver, train, snake, girl, fox, leopard, chair, tulip, telephone, couch, lamp, whale, otter, rabbit, bottle, cup, road, squirrel, skyscraper, snail, spider, turtle, kangaroo, tank, sea, bee, orange, dolphin, keyboard, poppy, palm_tree, crocodile, rose, castle, tractor, butterfly, table, seal, baby, mushroom, pear, dinosaur, bear, sunflower, cloud, man, wardrobe, bus, television