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_0140)
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 |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 140 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9991 |
| Val Accuracy | 0.8667 |
| Test Accuracy | 0.8684 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lawn_mower, pickup_truck, pine_tree, wardrobe, bridge, bus, television, motorcycle, wolf, butterfly, palm_tree, flatfish, willow_tree, rocket, sea, girl, dolphin, whale, beetle, raccoon, telephone, aquarium_fish, tank, ray, otter, cockroach, rabbit, house, porcupine, mountain, spider, sweet_pepper, hamster, bottle, cloud, snake, lamp, oak_tree, table, camel, forest, turtle, baby, leopard, dinosaur, sunflower, tiger, bowl, plate, maple_tree