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_0604)
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 | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 604 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9992 |
| Val Accuracy | 0.8997 |
| Test Accuracy | 0.8942 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
woman, bear, bus, chair, sea, camel, caterpillar, boy, man, porcupine, lobster, squirrel, rabbit, tulip, cockroach, chimpanzee, snail, beetle, bicycle, lawn_mower, possum, wolf, turtle, hamster, orchid, maple_tree, television, bowl, motorcycle, ray, cattle, flatfish, dinosaur, rocket, wardrobe, raccoon, orange, shark, sweet_pepper, willow_tree, skunk, otter, snake, bridge, mushroom, bee, forest, sunflower, rose, can