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_0492)
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 | 0.0001 |
| LR Scheduler | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 492 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9645 |
| Val Accuracy | 0.9000 |
| Test Accuracy | 0.8990 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
whale, pear, fox, tractor, television, chimpanzee, worm, rabbit, boy, butterfly, tank, willow_tree, forest, chair, beetle, castle, cockroach, palm_tree, couch, bicycle, skyscraper, skunk, camel, wardrobe, seal, bee, woman, lion, orchid, bus, ray, train, telephone, elephant, snail, mushroom, trout, dinosaur, spider, bottle, lobster, wolf, sea, bowl, cup, orange, lizard, kangaroo, clock, girl