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_0084)
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 | 0.0003 |
| LR Scheduler | linear |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 84 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 1.0000 |
| Val Accuracy | 0.8677 |
| Test Accuracy | 0.8522 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pickup_truck, skyscraper, maple_tree, snail, plate, tank, beaver, wolf, chair, snake, shrew, lobster, bed, kangaroo, whale, bowl, baby, telephone, willow_tree, tractor, crab, lion, sea, forest, cockroach, lizard, flatfish, bottle, bridge, sweet_pepper, tulip, cup, chimpanzee, bee, table, sunflower, keyboard, house, woman, tiger, mushroom, can, spider, leopard, orchid, dinosaur, pine_tree, ray, apple, clock