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_0234)
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 | 0.0001 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 234 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9258 |
| Val Accuracy | 0.8459 |
| Test Accuracy | 0.8618 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
road, plain, seal, trout, crocodile, possum, cloud, turtle, television, pickup_truck, mouse, cattle, bear, pine_tree, kangaroo, flatfish, forest, raccoon, woman, orchid, leopard, palm_tree, beaver, clock, streetcar, wolf, lamp, tulip, cockroach, chimpanzee, rose, bus, bed, telephone, sea, spider, otter, ray, maple_tree, apple, worm, snail, willow_tree, lion, sunflower, beetle, mountain, whale, baby, man