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_0812)
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 | 7e-05 |
| LR Scheduler | constant |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 812 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9942 |
| Val Accuracy | 0.8808 |
| Test Accuracy | 0.8634 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
television, maple_tree, camel, bus, sea, man, elephant, crocodile, forest, beaver, cattle, orchid, seal, cockroach, otter, couch, pear, shrew, porcupine, lamp, table, hamster, lawn_mower, willow_tree, road, snail, squirrel, aquarium_fish, can, dolphin, poppy, bridge, bottle, plate, flatfish, crab, girl, worm, keyboard, tiger, mountain, lion, streetcar, clock, skunk, bed, bear, bicycle, train, cloud