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_0208)
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 | test |
| 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 | 0.007 |
| Seed | 208 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9638 |
| Val Accuracy | 0.8744 |
| Test Accuracy | 0.8720 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sea, lizard, boy, butterfly, seal, chair, plate, flatfish, baby, leopard, mushroom, worm, pickup_truck, road, rocket, tulip, sunflower, table, house, poppy, bed, chimpanzee, tractor, caterpillar, snake, shrew, bottle, orange, train, crocodile, bridge, kangaroo, possum, apple, willow_tree, dinosaur, wolf, aquarium_fish, beaver, streetcar, cockroach, spider, couch, shark, plain, sweet_pepper, bus, crab, telephone, raccoon