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_0354)
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 | test |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 5e-05 |
| LR Scheduler | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 354 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9335 |
| Val Accuracy | 0.8443 |
| Test Accuracy | 0.8502 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
television, skunk, man, plate, bus, aquarium_fish, crab, boy, can, rose, tank, sunflower, forest, plain, couch, maple_tree, baby, skyscraper, squirrel, raccoon, mouse, beaver, lawn_mower, mountain, tiger, tractor, castle, mushroom, shark, shrew, ray, sea, pickup_truck, house, oak_tree, elephant, telephone, lizard, bridge, wardrobe, bowl, pine_tree, rabbit, girl, tulip, seal, turtle, pear, camel, worm