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_0196)
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 | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 196 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9146 |
| Val Accuracy | 0.7781 |
| Test Accuracy | 0.7780 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bridge, beetle, seal, bee, snail, aquarium_fish, worm, raccoon, lobster, clock, flatfish, crab, possum, table, hamster, caterpillar, kangaroo, bowl, otter, pine_tree, butterfly, ray, maple_tree, can, orchid, baby, snake, plain, shark, pickup_truck, cup, cattle, sea, wardrobe, cloud, sunflower, trout, cockroach, keyboard, elephant, palm_tree, poppy, woman, rose, mouse, lawn_mower, lamp, sweet_pepper, fox, rocket