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_0658)
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 | 0.0005 |
| LR Scheduler | constant |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 658 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5502 |
| Val Accuracy | 0.4301 |
| Test Accuracy | 0.4450 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mouse, mushroom, rabbit, motorcycle, otter, caterpillar, fox, elephant, bear, bee, dolphin, baby, wolf, keyboard, maple_tree, orchid, bed, lobster, oak_tree, ray, kangaroo, crab, flatfish, lion, man, streetcar, poppy, woman, shark, sweet_pepper, orange, leopard, tiger, bowl, aquarium_fish, beaver, forest, bus, couch, rose, telephone, road, rocket, porcupine, snake, clock, train, raccoon, trout, seal