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_0810)
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 |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 810 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9998 |
| Val Accuracy | 0.8917 |
| Test Accuracy | 0.8944 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lawn_mower, rose, tank, snail, road, telephone, bed, mouse, maple_tree, sunflower, bus, skyscraper, girl, mushroom, willow_tree, woman, whale, lobster, castle, chair, porcupine, bee, forest, tiger, sweet_pepper, hamster, skunk, chimpanzee, flatfish, beaver, motorcycle, table, can, palm_tree, house, lamp, crab, dolphin, spider, trout, lion, television, orchid, oak_tree, leopard, otter, apple, elephant, plain, man