ProbeX/Model-J__MAE__model_idx_0820

Model-J: MAE Model (model_idx_0820)

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	3e-05
LR Scheduler	cosine
Epochs	5
Max Train Steps	1665
Batch Size	64
Weight Decay	0.007
Seed	820
Random Crop	True
Random Flip	True

Performance

Metric	Value
Train Accuracy	0.9360
Val Accuracy	0.8784
Test Accuracy	0.8630

Training Categories

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

lobster, telephone, sweet_pepper, otter, lamp, lawn_mower, trout, sunflower, shark, tiger, spider, skunk, boy, bowl, elephant, willow_tree, porcupine, cloud, motorcycle, sea, wolf, tulip, cockroach, aquarium_fish, lizard, dolphin, chair, plain, oak_tree, forest, plate, ray, girl, bicycle, bus, house, snail, leopard, squirrel, beaver, palm_tree, caterpillar, seal, television, orange, streetcar, possum, camel, mouse, bed