ProbeX/Model-J__MAE__model_idx_0008

Model-J: MAE Model (model_idx_0008)

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	cosine_with_restarts
Epochs	2
Max Train Steps	666
Batch Size	64
Weight Decay	0.009
Seed	8
Random Crop	False
Random Flip	True

Performance

Metric	Value
Train Accuracy	0.7680
Val Accuracy	0.7013
Test Accuracy	0.7032

Training Categories

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

bus, clock, fox, boy, cockroach, worm, willow_tree, flatfish, bridge, turtle, table, chair, snake, chimpanzee, girl, snail, lobster, mouse, camel, rose, bottle, bicycle, bee, oak_tree, rocket, seal, rabbit, ray, forest, sweet_pepper, raccoon, hamster, leopard, beaver, tulip, wardrobe, wolf, lawn_mower, cattle, palm_tree, maple_tree, whale, baby, road, tractor, streetcar, crab, tank, orange, television