ProbeX/Model-J__MAE__model_idx_0006

Model-J: MAE Model (model_idx_0006)

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	0.0003
LR Scheduler	linear
Epochs	2
Max Train Steps	666
Batch Size	64
Weight Decay	0.03
Seed	6
Random Crop	True
Random Flip	True

Performance

Metric	Value
Train Accuracy	0.8256
Val Accuracy	0.7496
Test Accuracy	0.7654

Training Categories

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

pear, tulip, chimpanzee, clock, shrew, beetle, motorcycle, bowl, bridge, leopard, maple_tree, streetcar, woman, lobster, orchid, apple, train, lawn_mower, table, mouse, boy, cattle, lamp, rose, caterpillar, bee, orange, oak_tree, spider, rocket, elephant, bottle, butterfly, shark, forest, turtle, rabbit, bed, crab, lion, tiger, house, camel, skyscraper, tractor, sweet_pepper, cup, bus, snake, skunk