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_0416)
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 | test |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 3e-05 |
| LR Scheduler | constant |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 416 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9419 |
| Val Accuracy | 0.8656 |
| Test Accuracy | 0.8656 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dinosaur, can, chimpanzee, lawn_mower, hamster, clock, telephone, wardrobe, sunflower, skyscraper, apple, ray, baby, boy, bed, streetcar, cockroach, whale, rocket, turtle, leopard, plain, lizard, forest, maple_tree, seal, man, dolphin, crab, sweet_pepper, pear, wolf, couch, fox, aquarium_fish, mountain, otter, rabbit, cattle, television, bowl, raccoon, shrew, beaver, camel, house, keyboard, snake, bear, bee