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_0932)
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 | 9e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 932 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9971 |
| Val Accuracy | 0.8915 |
| Test Accuracy | 0.8996 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
aquarium_fish, lobster, pear, clock, mushroom, chimpanzee, beaver, crocodile, cattle, flatfish, woman, bottle, kangaroo, bowl, mountain, snail, willow_tree, shrew, seal, television, rocket, snake, cloud, apple, leopard, wolf, baby, orange, lawn_mower, boy, palm_tree, rose, motorcycle, bed, hamster, sunflower, crab, chair, turtle, tank, worm, can, house, elephant, fox, man, girl, bee, bicycle, keyboard