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_0993)
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 | 0.0001 |
| LR Scheduler | linear |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 993 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9893 |
| Val Accuracy | 0.8816 |
| Test Accuracy | 0.8940 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
spider, road, flatfish, wardrobe, apple, bowl, crab, butterfly, bottle, beaver, chimpanzee, orchid, house, sea, squirrel, dolphin, tulip, skunk, oak_tree, kangaroo, cattle, palm_tree, bridge, bear, pear, orange, sweet_pepper, aquarium_fish, caterpillar, pine_tree, poppy, raccoon, cup, rabbit, turtle, table, girl, forest, couch, train, streetcar, skyscraper, can, trout, otter, shark, plain, pickup_truck, fox, beetle