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_0256)
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 | test |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 256 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9997 |
| Val Accuracy | 0.8768 |
| Test Accuracy | 0.8910 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
boy, dolphin, man, sweet_pepper, skyscraper, trout, keyboard, sea, hamster, lobster, orchid, bowl, flatfish, whale, wardrobe, turtle, orange, shrew, chair, cattle, tulip, snail, palm_tree, telephone, woman, television, aquarium_fish, skunk, snake, crocodile, castle, cup, pear, possum, dinosaur, lion, baby, bee, mountain, tank, shark, worm, rose, lamp, chimpanzee, poppy, cockroach, pine_tree, tiger, seal