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_0805)
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 | 9e-05 |
| LR Scheduler | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 805 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9985 |
| Val Accuracy | 0.8893 |
| Test Accuracy | 0.8906 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tractor, bee, cattle, maple_tree, skunk, orchid, mountain, turtle, woman, fox, forest, man, elephant, clock, pine_tree, tulip, beaver, porcupine, bridge, kangaroo, apple, lion, plain, rose, snake, bus, willow_tree, butterfly, dinosaur, hamster, leopard, seal, wardrobe, cockroach, poppy, lamp, aquarium_fish, whale, cloud, cup, bicycle, chair, lobster, bed, sea, boy, pickup_truck, crab, mouse, trout