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_0893)
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 | cosine_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 893 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9956 |
| Val Accuracy | 0.8659 |
| Test Accuracy | 0.8742 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sea, bus, plate, woman, palm_tree, girl, lion, cockroach, squirrel, couch, cup, shark, lamp, turtle, dinosaur, tulip, television, motorcycle, forest, boy, poppy, raccoon, beaver, dolphin, skunk, snail, cloud, tank, bowl, pine_tree, shrew, clock, bridge, table, lobster, possum, pickup_truck, fox, chimpanzee, lawn_mower, kangaroo, porcupine, keyboard, spider, bicycle, cattle, house, mountain, apple, oak_tree