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_0650)
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 | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 650 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9385 |
| Val Accuracy | 0.5779 |
| Test Accuracy | 0.5810 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
whale, kangaroo, clock, streetcar, rose, couch, bee, cloud, house, spider, possum, television, chair, elephant, plate, rabbit, wardrobe, poppy, girl, tulip, bed, sunflower, bottle, palm_tree, sweet_pepper, oak_tree, tank, cockroach, tractor, chimpanzee, train, cup, raccoon, trout, orange, crocodile, pear, butterfly, squirrel, ray, dinosaur, beetle, man, willow_tree, rocket, table, aquarium_fish, mountain, pickup_truck, snail