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_0692)
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 | val |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 692 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9274 |
| Val Accuracy | 0.5635 |
| Test Accuracy | 0.5634 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
spider, bridge, shark, crocodile, squirrel, chair, porcupine, bottle, caterpillar, plain, sea, dinosaur, trout, orchid, lobster, mountain, bowl, house, raccoon, tulip, girl, skunk, turtle, camel, wolf, man, skyscraper, oak_tree, worm, beetle, otter, castle, lawn_mower, woman, poppy, whale, bed, plate, table, cockroach, motorcycle, willow_tree, aquarium_fish, can, mouse, snake, bicycle, pickup_truck, baby, telephone