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_0731)
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 | 9e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 731 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9996 |
| Val Accuracy | 0.9149 |
| Test Accuracy | 0.9120 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
fox, aquarium_fish, orange, can, wardrobe, ray, tulip, dolphin, trout, orchid, woman, otter, couch, bear, bridge, forest, mouse, bed, elephant, streetcar, bicycle, skunk, shrew, whale, bowl, beetle, sea, cup, kangaroo, raccoon, leopard, bottle, road, rocket, lawn_mower, bus, shark, chimpanzee, cockroach, lion, sweet_pepper, pear, crocodile, poppy, cattle, pickup_truck, lobster, plain, skyscraper, keyboard