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_0200)
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 | constant |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 200 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9769 |
| Val Accuracy | 0.8592 |
| Test Accuracy | 0.8552 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
oak_tree, turtle, pine_tree, aquarium_fish, skyscraper, tiger, camel, skunk, snail, lion, poppy, beaver, trout, television, pear, otter, whale, lobster, mountain, shrew, plain, mushroom, baby, tank, ray, castle, shark, chair, dolphin, telephone, orchid, raccoon, cockroach, sea, seal, keyboard, can, wardrobe, crab, cattle, plate, table, hamster, boy, crocodile, bowl, man, tulip, squirrel, mouse