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_0848)
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 | test |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 848 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9748 |
| Val Accuracy | 0.8763 |
| Test Accuracy | 0.8534 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lawn_mower, tiger, worm, pickup_truck, pear, elephant, seal, man, sunflower, bus, rose, maple_tree, bicycle, flatfish, porcupine, train, palm_tree, snail, hamster, table, lobster, whale, mountain, girl, rocket, oak_tree, cockroach, trout, bed, skyscraper, chair, willow_tree, clock, boy, otter, wolf, sea, apple, cattle, plate, leopard, orange, cup, kangaroo, pine_tree, shrew, couch, possum, television, sweet_pepper