Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0563)
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 | val |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 563 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9751 |
| Val Accuracy | 0.8576 |
| Test Accuracy | 0.8538 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
seal, forest, plain, otter, fox, cup, mouse, oak_tree, clock, cattle, tank, dinosaur, mushroom, elephant, butterfly, bicycle, skyscraper, wolf, couch, bowl, snail, pickup_truck, rabbit, man, lobster, raccoon, willow_tree, hamster, lamp, keyboard, snake, woman, trout, dolphin, turtle, girl, table, bottle, tulip, palm_tree, sweet_pepper, apple, telephone, flatfish, bee, sea, lizard, motorcycle, baby, whale
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0563
Base model
facebook/vit-mae-base