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_0109)
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 | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 109 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9017 |
| Val Accuracy | 0.8299 |
| Test Accuracy | 0.8122 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
streetcar, crocodile, sea, couch, clock, oak_tree, television, camel, dinosaur, woman, pear, seal, bottle, lion, tractor, kangaroo, road, leopard, house, flatfish, plate, bus, bowl, baby, snail, can, dolphin, mountain, wolf, pickup_truck, squirrel, butterfly, cockroach, castle, tulip, table, possum, train, otter, lamp, keyboard, elephant, whale, telephone, fox, apple, caterpillar, hamster, orange, willow_tree