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_0242)
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 | test |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 242 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8443 |
| Val Accuracy | 0.7589 |
| Test Accuracy | 0.7544 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
camel, sea, tank, skunk, baby, house, bottle, aquarium_fish, dolphin, bee, bowl, boy, porcupine, tiger, bridge, can, girl, clock, television, dinosaur, poppy, mountain, forest, shark, lion, plain, orange, elephant, beaver, table, possum, cup, rabbit, bus, willow_tree, flatfish, mouse, plate, wolf, oak_tree, cloud, man, couch, butterfly, ray, hamster, rose, sunflower, tractor, palm_tree