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_0502)
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 | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 502 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9676 |
| Val Accuracy | 0.8691 |
| Test Accuracy | 0.8672 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
streetcar, telephone, willow_tree, orange, possum, trout, spider, rose, lawn_mower, camel, lion, mouse, dolphin, bicycle, television, chair, wolf, raccoon, plate, kangaroo, turtle, porcupine, castle, tank, cloud, fox, table, snake, crab, bowl, crocodile, hamster, clock, apple, butterfly, whale, worm, dinosaur, aquarium_fish, mountain, bus, chimpanzee, man, otter, motorcycle, skyscraper, forest, lobster, flatfish, pine_tree