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_0680)
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 | 7e-05 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 680 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9991 |
| Val Accuracy | 0.8971 |
| Test Accuracy | 0.9064 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
wardrobe, shrew, mouse, sea, bear, road, elephant, raccoon, forest, dolphin, lion, beaver, aquarium_fish, mushroom, orange, tiger, sweet_pepper, dinosaur, rabbit, cattle, ray, beetle, camel, leopard, orchid, boy, pine_tree, bridge, rose, mountain, willow_tree, cup, snake, crab, turtle, telephone, poppy, trout, train, sunflower, chair, cloud, spider, bus, skyscraper, crocodile, lizard, pear, palm_tree, rocket