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_0403)
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 | 3e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 403 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9968 |
| Val Accuracy | 0.8811 |
| Test Accuracy | 0.8818 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bowl, table, dolphin, rabbit, mountain, orchid, trout, couch, wardrobe, clock, forest, beetle, pickup_truck, willow_tree, porcupine, chair, crocodile, wolf, flatfish, crab, road, skyscraper, plain, maple_tree, otter, bottle, castle, train, leopard, bed, girl, tractor, butterfly, bus, camel, sunflower, tank, house, bicycle, snake, shark, baby, television, aquarium_fish, worm, kangaroo, boy, lizard, mouse, skunk