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_0155)
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 | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 155 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9866 |
| Val Accuracy | 0.8707 |
| Test Accuracy | 0.8668 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lion, bee, mushroom, beaver, shark, woman, telephone, lizard, tractor, rocket, raccoon, whale, rabbit, house, skyscraper, maple_tree, orchid, chair, kangaroo, can, hamster, bus, bridge, tulip, chimpanzee, oak_tree, baby, squirrel, tiger, rose, lamp, butterfly, snail, pear, crab, mouse, couch, cattle, pine_tree, cup, lobster, beetle, cockroach, bowl, mountain, trout, sea, palm_tree, fox, streetcar