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_0991)
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 | 0.0005 |
| LR Scheduler | constant |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 991 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6899 |
| Val Accuracy | 0.4997 |
| Test Accuracy | 0.4886 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
poppy, woman, shark, rabbit, turtle, television, caterpillar, girl, snail, boy, lobster, lawn_mower, lamp, whale, porcupine, sweet_pepper, man, butterfly, skunk, dolphin, hamster, beaver, worm, otter, castle, bed, maple_tree, tiger, cattle, rose, mushroom, plate, bridge, aquarium_fish, spider, fox, bee, oak_tree, crocodile, crab, cockroach, willow_tree, telephone, tank, plain, pickup_truck, sea, snake, bowl, camel