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_0799)
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 | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 799 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9034 |
| Val Accuracy | 0.8301 |
| Test Accuracy | 0.8278 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
raccoon, snake, house, road, clock, mushroom, kangaroo, boy, bus, trout, telephone, chair, oak_tree, tractor, shrew, lizard, tank, leopard, willow_tree, hamster, bear, turtle, can, cockroach, keyboard, flatfish, lobster, pine_tree, woman, table, aquarium_fish, possum, rose, poppy, butterfly, bicycle, lion, wolf, girl, skunk, plate, maple_tree, wardrobe, man, tulip, dolphin, baby, lawn_mower, dinosaur, elephant