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_0926)
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 | 0.0003 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 926 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9983 |
| Val Accuracy | 0.8667 |
| Test Accuracy | 0.8668 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mouse, butterfly, can, worm, ray, orchid, flatfish, table, caterpillar, mountain, raccoon, cup, sweet_pepper, couch, cockroach, cloud, crocodile, skunk, bus, kangaroo, palm_tree, rose, possum, crab, beetle, baby, lawn_mower, lion, clock, keyboard, forest, tulip, beaver, lizard, whale, aquarium_fish, snail, trout, woman, lamp, snake, hamster, boy, squirrel, spider, camel, bowl, porcupine, apple, willow_tree