Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0769)
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 | 9e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 769 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9407 |
| Val Accuracy | 0.8424 |
| Test Accuracy | 0.8492 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
raccoon, tulip, bridge, snail, whale, television, sea, hamster, forest, palm_tree, shrew, snake, mushroom, boy, lamp, cockroach, keyboard, bee, otter, poppy, crab, girl, butterfly, leopard, mountain, possum, tractor, cattle, bear, willow_tree, fox, bus, kangaroo, dolphin, bicycle, house, telephone, orange, squirrel, man, skunk, sweet_pepper, pickup_truck, bed, chimpanzee, rose, ray, streetcar, chair, flatfish
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0769
Base model
facebook/vit-mae-base