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_0002)
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 | 0.0001 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 2 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9996 |
| Val Accuracy | 0.9000 |
| Test Accuracy | 0.9040 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
crab, man, trout, television, skyscraper, rabbit, whale, mouse, snake, clock, dolphin, wardrobe, cup, elephant, bear, lamp, pickup_truck, cockroach, tiger, motorcycle, rose, beaver, kangaroo, aquarium_fish, woman, willow_tree, bowl, couch, girl, cloud, keyboard, worm, chimpanzee, sea, lion, road, butterfly, plain, spider, poppy, apple, can, pine_tree, train, rocket, porcupine, squirrel, mountain, fox, bee