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_0437)
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 | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 437 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9634 |
| Val Accuracy | 0.7597 |
| Test Accuracy | 0.7560 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cockroach, can, porcupine, crocodile, tank, shrew, wardrobe, elephant, castle, maple_tree, bottle, fox, turtle, forest, telephone, cattle, lamp, caterpillar, cup, mouse, bridge, beaver, skyscraper, tulip, keyboard, seal, rocket, rabbit, lion, sea, camel, ray, motorcycle, shark, lobster, bowl, chimpanzee, hamster, spider, orange, bicycle, girl, man, clock, cloud, rose, oak_tree, kangaroo, woman, bee