ProbeX/Model-J__MAE__model_idx_0009

Model-J: MAE Model (model_idx_0009)

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	9e-05
LR Scheduler	cosine_with_restarts
Epochs	2
Max Train Steps	666
Batch Size	64
Weight Decay	0.009
Seed	9
Random Crop	True
Random Flip	False

Performance

Metric	Value
Train Accuracy	0.9194
Val Accuracy	0.8640
Test Accuracy	0.8602

Training Categories

The model was fine-tuned on the following 50 CIFAR100 classes:

orange, whale, plain, wolf, dinosaur, bear, lawn_mower, bridge, camel, telephone, house, baby, tank, lamp, lion, sea, palm_tree, tiger, aquarium_fish, pine_tree, leopard, cloud, woman, pear, trout, girl, train, bicycle, squirrel, apple, forest, plate, rose, table, shrew, seal, fox, raccoon, elephant, sunflower, can, poppy, oak_tree, lizard, mushroom, cattle, tulip, bus, crab, maple_tree