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_0420)
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 | 0.0005 |
| LR Scheduler | constant |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 420 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5445 |
| Val Accuracy | 0.4405 |
| Test Accuracy | 0.4380 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bed, porcupine, streetcar, snake, pickup_truck, mushroom, whale, bowl, cockroach, seal, oak_tree, wardrobe, raccoon, tulip, sea, clock, crab, pear, bicycle, pine_tree, mouse, bus, possum, beaver, shark, motorcycle, beetle, train, keyboard, rabbit, orchid, camel, orange, lobster, spider, aquarium_fish, flatfish, lizard, cloud, dolphin, forest, willow_tree, television, wolf, caterpillar, apple, shrew, palm_tree, tank, snail