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_0144)
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 | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 144 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9525 |
| Val Accuracy | 0.7296 |
| Test Accuracy | 0.7214 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
squirrel, apple, tiger, lion, porcupine, palm_tree, flatfish, turtle, lizard, lobster, hamster, forest, ray, cattle, mountain, skunk, sunflower, boy, couch, lawn_mower, chair, cockroach, clock, possum, rocket, woman, aquarium_fish, bicycle, road, orange, can, plain, castle, house, train, dolphin, wolf, shark, girl, sweet_pepper, crab, snail, bear, butterfly, telephone, man, raccoon, bus, maple_tree, caterpillar