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_0228)
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 | constant |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 228 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9017 |
| Val Accuracy | 0.7581 |
| Test Accuracy | 0.7604 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
butterfly, house, plate, aquarium_fish, raccoon, camel, leopard, wolf, cup, clock, lion, trout, shrew, boy, plain, maple_tree, rabbit, couch, lamp, caterpillar, porcupine, woman, lawn_mower, man, mountain, can, whale, bed, tractor, cockroach, lobster, castle, flatfish, pine_tree, seal, streetcar, chimpanzee, dolphin, cattle, television, bus, table, skunk, road, train, beaver, orange, cloud, willow_tree, baby