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_0396)
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 | cosine_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 396 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9879 |
| Val Accuracy | 0.8885 |
| Test Accuracy | 0.8966 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
aquarium_fish, sea, elephant, poppy, plain, motorcycle, can, road, flatfish, crocodile, butterfly, lizard, chair, table, man, apple, camel, telephone, oak_tree, pear, otter, seal, orchid, chimpanzee, lobster, bear, couch, dinosaur, kangaroo, cockroach, maple_tree, raccoon, skunk, crab, lawn_mower, bed, tank, snail, leopard, shark, pickup_truck, streetcar, clock, cup, cattle, pine_tree, rocket, whale, wardrobe, boy