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_0337)
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 | val |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 337 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9913 |
| Val Accuracy | 0.8893 |
| Test Accuracy | 0.8936 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bowl, wardrobe, flatfish, elephant, rabbit, bicycle, kangaroo, train, lamp, chair, chimpanzee, camel, dinosaur, pickup_truck, cup, shark, turtle, can, plate, house, bottle, willow_tree, bee, orchid, otter, tank, worm, tulip, seal, cockroach, butterfly, apple, woman, raccoon, orange, crab, spider, snake, sea, table, skunk, castle, sweet_pepper, maple_tree, streetcar, shrew, plain, man, possum, bus