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_0198)
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 | val |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | constant |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 198 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9882 |
| Val Accuracy | 0.8773 |
| Test Accuracy | 0.8648 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
elephant, crab, man, bicycle, bottle, house, wardrobe, apple, bee, telephone, wolf, motorcycle, caterpillar, lawn_mower, aquarium_fish, crocodile, tulip, keyboard, flatfish, willow_tree, shrew, orchid, mouse, kangaroo, raccoon, couch, cockroach, oak_tree, lizard, baby, beetle, trout, rose, dinosaur, bridge, camel, poppy, sweet_pepper, leopard, clock, sea, woman, can, fox, lamp, bus, skunk, chair, cattle, ray