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_0430)
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 | 0.0001 |
| LR Scheduler | constant_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 430 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9420 |
| Val Accuracy | 0.8536 |
| Test Accuracy | 0.8518 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tiger, elephant, can, poppy, oak_tree, lion, kangaroo, sea, flatfish, bear, willow_tree, shark, lawn_mower, mouse, porcupine, chimpanzee, wolf, house, aquarium_fish, bowl, tank, bee, table, motorcycle, rocket, lamp, woman, tulip, road, pickup_truck, bus, plate, couch, shrew, boy, hamster, plain, man, sunflower, skunk, television, possum, rabbit, wardrobe, crab, fox, raccoon, sweet_pepper, caterpillar, skyscraper