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_0807)
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 | 3e-05 |
| LR Scheduler | cosine |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 807 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9933 |
| Val Accuracy | 0.8957 |
| Test Accuracy | 0.8902 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
keyboard, motorcycle, cloud, cattle, shrew, worm, shark, plain, orange, couch, pine_tree, girl, bowl, telephone, mountain, raccoon, television, lamp, butterfly, road, dolphin, hamster, turtle, streetcar, camel, bottle, orchid, rabbit, man, bicycle, ray, porcupine, palm_tree, rocket, chair, sea, pickup_truck, leopard, crab, sweet_pepper, cup, plate, skyscraper, house, caterpillar, wolf, possum, rose, can, tank