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_0427)
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_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 427 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8682 |
| Val Accuracy | 0.8155 |
| Test Accuracy | 0.8156 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
seal, dinosaur, cloud, bicycle, snake, streetcar, boy, keyboard, can, bus, cup, forest, man, lamp, skyscraper, willow_tree, woman, whale, baby, maple_tree, rabbit, oak_tree, aquarium_fish, bowl, shark, house, squirrel, tank, pickup_truck, beaver, bee, train, lawn_mower, elephant, tiger, tulip, shrew, cockroach, wardrobe, pear, hamster, raccoon, possum, mushroom, palm_tree, castle, apple, tractor, lion, porcupine