Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0044)
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 | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 44 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.9051 |
| Test Accuracy | 0.8908 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cup, cattle, dinosaur, sweet_pepper, rose, rocket, poppy, telephone, bicycle, pickup_truck, skunk, shark, beaver, fox, bottle, hamster, caterpillar, oak_tree, tractor, lizard, raccoon, bus, crab, sunflower, willow_tree, clock, orange, mushroom, kangaroo, girl, snake, house, lobster, apple, leopard, whale, maple_tree, can, castle, dolphin, woman, chair, butterfly, couch, road, tulip, otter, chimpanzee, aquarium_fish, trout
- Downloads last month
- 1
Model tree for ProbeX/Model-J__MAE__model_idx_0044
Base model
facebook/vit-mae-base