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_0340)
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 | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 340 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8784 |
| Val Accuracy | 0.8179 |
| Test Accuracy | 0.8308 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
couch, sunflower, shark, mountain, otter, fox, forest, crocodile, kangaroo, mouse, table, pickup_truck, dolphin, streetcar, flatfish, beetle, crab, camel, keyboard, caterpillar, tiger, cattle, rocket, television, shrew, plate, orange, sea, lion, whale, apple, clock, bear, bed, lizard, aquarium_fish, trout, tractor, sweet_pepper, spider, maple_tree, bicycle, bus, motorcycle, cloud, wolf, telephone, pine_tree, lobster, bridge