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_0369)
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 | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 369 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6536 |
| Val Accuracy | 0.5387 |
| Test Accuracy | 0.5352 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sweet_pepper, beetle, squirrel, clock, fox, maple_tree, chair, flatfish, tank, turtle, house, lion, cockroach, tiger, oak_tree, camel, possum, road, rocket, kangaroo, aquarium_fish, dinosaur, girl, raccoon, shark, porcupine, sunflower, motorcycle, bottle, orange, sea, dolphin, poppy, wardrobe, willow_tree, castle, keyboard, couch, beaver, trout, table, pickup_truck, lamp, plain, leopard, man, whale, bear, crocodile, snake