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_0421)
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 | 5e-05 |
| LR Scheduler | linear |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 421 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9974 |
| Val Accuracy | 0.9043 |
| Test Accuracy | 0.8898 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
poppy, trout, shark, girl, bowl, mushroom, keyboard, orange, sea, willow_tree, house, lion, mountain, couch, dinosaur, beaver, kangaroo, sweet_pepper, possum, turtle, cockroach, television, telephone, oak_tree, camel, lizard, bus, whale, spider, wardrobe, lobster, cup, tank, castle, beetle, bed, snail, aquarium_fish, raccoon, chair, palm_tree, orchid, maple_tree, man, pickup_truck, clock, wolf, boy, bicycle, plain