Model-J: MAE Model (model_idx_0277)
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
ProbeXModel 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 | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 277 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|
| Train Accuracy | 0.9966 |
| Val Accuracy | 0.8360 |
| Test Accuracy | 0.8226 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
maple_tree, rabbit, motorcycle, sweet_pepper, chair, castle, train, man, leopard, rose, trout, girl, lion, pine_tree, telephone, butterfly, keyboard, orange, squirrel, can, table, road, bicycle, house, bed, ray, kangaroo, rocket, hamster, shark, baby, mouse, tank, bowl, plate, wardrobe, pickup_truck, lamp, tiger, tulip, possum, seal, turtle, shrew, cockroach, willow_tree, raccoon, snake, lawn_mower, chimpanzee
