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_0665)
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 | 0.0003 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 665 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 1.0000 |
| Val Accuracy | 0.8536 |
| Test Accuracy | 0.8482 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
couch, turtle, sea, mushroom, tulip, girl, lobster, keyboard, maple_tree, dinosaur, tank, oak_tree, chimpanzee, streetcar, boy, spider, cup, kangaroo, tractor, pickup_truck, lizard, clock, lamp, skunk, house, shark, leopard, mountain, palm_tree, elephant, wolf, telephone, road, snake, woman, bridge, squirrel, porcupine, sweet_pepper, willow_tree, table, pear, crocodile, motorcycle, bicycle, ray, rocket, orchid, aquarium_fish, forest