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_0375)
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 | 3e-05 |
| LR Scheduler | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 375 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8726 |
| Val Accuracy | 0.8035 |
| Test Accuracy | 0.8218 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
man, leopard, rose, shrew, mushroom, wardrobe, bridge, clock, chair, castle, snake, wolf, palm_tree, aquarium_fish, mouse, tank, butterfly, seal, apple, rocket, fox, dolphin, sea, chimpanzee, otter, orchid, beaver, cloud, pear, poppy, rabbit, tulip, skunk, boy, keyboard, lizard, camel, willow_tree, baby, possum, trout, orange, bee, motorcycle, turtle, shark, sunflower, streetcar, cup, tiger