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_0581)
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 | 5e-05 |
| LR Scheduler | linear |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 581 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 1.0000 |
| Val Accuracy | 0.8963 |
| Test Accuracy | 0.9022 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
shark, clock, chimpanzee, cloud, cup, forest, crab, tank, sweet_pepper, television, baby, turtle, bridge, pear, pickup_truck, seal, lobster, cockroach, keyboard, rose, crocodile, apple, fox, boy, beaver, poppy, skyscraper, ray, lamp, road, dinosaur, mountain, beetle, orange, willow_tree, motorcycle, camel, bee, rocket, butterfly, bottle, trout, tiger, palm_tree, bowl, sea, elephant, train, squirrel, plate