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_0365)
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 | 3e-05 |
| LR Scheduler | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 365 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8703 |
| Val Accuracy | 0.8389 |
| Test Accuracy | 0.8322 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
wardrobe, otter, pickup_truck, motorcycle, chimpanzee, poppy, woman, trout, squirrel, sunflower, bowl, fox, bed, rose, porcupine, leopard, house, apple, bottle, castle, chair, wolf, keyboard, bear, cloud, lion, orchid, can, turtle, rabbit, sea, whale, baby, skyscraper, lobster, beetle, girl, oak_tree, snake, clock, rocket, cockroach, beaver, crocodile, pear, cup, mouse, mountain, dolphin, palm_tree