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_0193)
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 | 0.0005 |
| LR Scheduler | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 193 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6454 |
| Val Accuracy | 0.5256 |
| Test Accuracy | 0.5314 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
skunk, television, road, woman, maple_tree, camel, beaver, tractor, keyboard, crocodile, baby, mushroom, boy, table, oak_tree, rose, can, bus, possum, raccoon, dolphin, bear, mountain, chair, pickup_truck, castle, elephant, sea, mouse, poppy, bowl, caterpillar, otter, cup, worm, cockroach, train, motorcycle, wardrobe, turtle, hamster, wolf, willow_tree, plate, bottle, lizard, seal, orange, telephone, skyscraper