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_0406)
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 | constant |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 406 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9130 |
| Val Accuracy | 0.7797 |
| Test Accuracy | 0.7810 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
snail, sweet_pepper, lizard, beaver, willow_tree, possum, caterpillar, oak_tree, bee, rabbit, mushroom, tulip, trout, porcupine, bridge, aquarium_fish, lamp, maple_tree, house, palm_tree, sunflower, dinosaur, kangaroo, girl, lion, mountain, hamster, chair, cockroach, orange, train, plate, streetcar, bus, bed, otter, snake, tank, man, cattle, television, orchid, fox, cloud, bowl, elephant, crab, rocket, poppy, telephone