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_0418)
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 | 9e-05 |
| LR Scheduler | linear |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 418 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9512 |
| Val Accuracy | 0.8851 |
| Test Accuracy | 0.8806 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tractor, rose, whale, table, clock, dolphin, couch, dinosaur, aquarium_fish, ray, bed, plain, palm_tree, pine_tree, shrew, snail, elephant, girl, leopard, television, streetcar, beetle, plate, poppy, telephone, mountain, baby, sea, bicycle, bowl, wardrobe, road, flatfish, fox, lamp, house, bottle, willow_tree, cockroach, shark, chimpanzee, possum, tank, sweet_pepper, squirrel, tiger, porcupine, bridge, trout, butterfly