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_0925)
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 | val |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0003 |
| LR Scheduler | linear |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 925 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9747 |
| Val Accuracy | 0.7581 |
| Test Accuracy | 0.7660 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bicycle, cup, television, apple, palm_tree, mountain, shrew, man, orchid, baby, road, kangaroo, crocodile, fox, spider, ray, boy, lobster, tiger, snail, oak_tree, whale, lion, camel, girl, sea, streetcar, bus, worm, train, bottle, cattle, poppy, tulip, forest, lizard, butterfly, lamp, wolf, seal, cockroach, bear, clock, snake, pine_tree, skyscraper, sunflower, woman, beaver, bowl