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_0289)
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 |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 289 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7133 |
| Val Accuracy | 0.5275 |
| Test Accuracy | 0.5280 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
train, television, cup, tank, road, snail, mouse, leopard, aquarium_fish, cockroach, couch, plate, bed, tractor, crab, can, tiger, bus, sea, apple, ray, motorcycle, fox, castle, lion, wolf, beaver, table, cloud, camel, tulip, possum, orchid, flatfish, oak_tree, baby, shark, keyboard, worm, kangaroo, mushroom, boy, chair, porcupine, girl, pickup_truck, bowl, streetcar, house, pear