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_0397)
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 | constant |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 397 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8938 |
| Val Accuracy | 0.8459 |
| Test Accuracy | 0.8402 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bridge, crocodile, chimpanzee, fox, possum, elephant, poppy, television, can, orchid, motorcycle, skunk, sweet_pepper, table, rabbit, dinosaur, willow_tree, cattle, snail, cockroach, flatfish, skyscraper, leopard, orange, mushroom, raccoon, pine_tree, bear, castle, beaver, rose, man, pear, clock, squirrel, crab, cup, bus, caterpillar, chair, shark, porcupine, pickup_truck, maple_tree, turtle, bee, lobster, telephone, plain, streetcar