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_0574)
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 | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 574 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9672 |
| Val Accuracy | 0.8507 |
| Test Accuracy | 0.8520 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
table, bridge, whale, camel, spider, girl, road, lion, lamp, motorcycle, bus, mountain, squirrel, beaver, tiger, shark, boy, rose, rabbit, keyboard, possum, snail, plate, bottle, dinosaur, porcupine, chimpanzee, couch, train, rocket, fox, lizard, television, plain, skyscraper, house, kangaroo, mouse, castle, streetcar, mushroom, elephant, butterfly, tractor, tank, can, turtle, dolphin, tulip, raccoon