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_0831)
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 | cosine_with_restarts |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 831 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6587 |
| Val Accuracy | 0.5269 |
| Test Accuracy | 0.5296 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pine_tree, mushroom, palm_tree, worm, bottle, rabbit, motorcycle, bear, crab, squirrel, shark, plain, bus, ray, crocodile, aquarium_fish, plate, chair, snail, tulip, elephant, bridge, oak_tree, bed, pickup_truck, whale, streetcar, caterpillar, leopard, television, beaver, porcupine, house, telephone, lamp, willow_tree, raccoon, lobster, man, boy, cattle, cloud, mouse, lizard, tractor, butterfly, turtle, sea, castle, cup