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_0718)
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 | cosine |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 718 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5127 |
| Val Accuracy | 0.4656 |
| Test Accuracy | 0.4664 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cockroach, bicycle, butterfly, caterpillar, seal, kangaroo, lion, dinosaur, bed, orchid, crocodile, cup, bus, dolphin, train, shrew, road, snail, keyboard, trout, girl, house, wolf, orange, skunk, mushroom, cloud, rocket, shark, maple_tree, tulip, skyscraper, plate, tractor, pickup_truck, boy, worm, chair, bee, man, oak_tree, porcupine, lizard, cattle, sea, squirrel, ray, pine_tree, mountain, possum