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_0423)
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 | 9e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 423 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9163 |
| Val Accuracy | 0.8573 |
| Test Accuracy | 0.8524 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
can, tulip, trout, pine_tree, boy, couch, bed, orange, pickup_truck, bicycle, maple_tree, elephant, keyboard, lion, aquarium_fish, wolf, clock, dolphin, shrew, beetle, porcupine, plate, tank, motorcycle, hamster, caterpillar, skyscraper, skunk, oak_tree, willow_tree, cup, tiger, lawn_mower, lamp, pear, beaver, possum, otter, bowl, snail, snake, cockroach, squirrel, bear, castle, sweet_pepper, chair, girl, sea, worm