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_0052)
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 | val |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 3e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 52 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9149 |
| Val Accuracy | 0.8232 |
| Test Accuracy | 0.8232 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
girl, trout, cloud, flatfish, snail, boy, cattle, porcupine, oak_tree, beetle, raccoon, mushroom, leopard, camel, cockroach, rocket, whale, lamp, tiger, bed, aquarium_fish, pine_tree, plain, sunflower, palm_tree, lobster, forest, dolphin, castle, rose, ray, plate, table, lizard, poppy, clock, cup, streetcar, can, beaver, maple_tree, woman, mountain, tank, dinosaur, spider, crab, willow_tree, man, kangaroo