Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0954)
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 | 3e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 954 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9398 |
| Val Accuracy | 0.8365 |
| Test Accuracy | 0.8450 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
orange, sea, raccoon, bee, tulip, chair, porcupine, train, poppy, cloud, sunflower, plate, palm_tree, beaver, girl, bus, seal, mouse, cattle, cockroach, dolphin, bridge, baby, camel, snake, turtle, dinosaur, crab, can, bed, fox, road, house, trout, beetle, lamp, chimpanzee, lobster, ray, streetcar, woman, forest, couch, motorcycle, willow_tree, leopard, tank, table, rabbit, apple
- Downloads last month
- 1
Model tree for ProbeX/Model-J__MAE__model_idx_0954
Base model
facebook/vit-mae-base