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_0797)
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 | 3e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 797 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9992 |
| Val Accuracy | 0.8707 |
| Test Accuracy | 0.8638 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
oak_tree, turtle, caterpillar, tiger, bear, television, sweet_pepper, dolphin, bowl, man, cattle, skunk, table, castle, lizard, leopard, bed, house, train, orchid, mushroom, kangaroo, shark, rabbit, possum, plain, woman, forest, sunflower, couch, clock, crab, elephant, camel, raccoon, girl, otter, mouse, wolf, streetcar, porcupine, poppy, lamp, can, bus, snake, squirrel, bottle, pear, maple_tree