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_0573)
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 | 0.05 |
| Seed | 573 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6863 |
| Val Accuracy | 0.4931 |
| Test Accuracy | 0.5150 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dolphin, seal, pear, bus, poppy, bear, kangaroo, cattle, house, tractor, turtle, flatfish, chimpanzee, ray, snake, plain, sea, tank, camel, chair, bridge, sunflower, squirrel, bottle, mushroom, clock, tiger, hamster, motorcycle, porcupine, bed, palm_tree, lizard, shark, skunk, crab, spider, willow_tree, road, couch, tulip, dinosaur, skyscraper, mountain, elephant, possum, aquarium_fish, television, fox, lamp