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_0506)
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 | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 506 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8967 |
| Val Accuracy | 0.8261 |
| Test Accuracy | 0.8202 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
kangaroo, girl, tulip, oak_tree, turtle, chimpanzee, pine_tree, pickup_truck, lizard, couch, snake, man, leopard, worm, bee, snail, fox, plain, streetcar, sweet_pepper, hamster, train, willow_tree, camel, baby, shrew, table, house, telephone, keyboard, can, poppy, plate, cup, tiger, lobster, bowl, mouse, rocket, ray, motorcycle, orchid, crab, crocodile, orange, clock, beaver, butterfly, castle, cockroach