metadata
base_model: facebook/vit-mae-base
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: MAE Model (model_idx_0681)
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 | test |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 681 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9378 |
| Val Accuracy | 0.8427 |
| Test Accuracy | 0.8520 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
baby, lamp, forest, train, poppy, plate, beetle, road, rocket, maple_tree, shark, lawn_mower, clock, cup, aquarium_fish, plain, snail, turtle, worm, can, squirrel, palm_tree, sweet_pepper, caterpillar, pear, sea, bottle, crocodile, lobster, pickup_truck, skyscraper, couch, chimpanzee, streetcar, rabbit, skunk, crab, whale, kangaroo, shrew, castle, bridge, beaver, otter, spider, woman, orchid, mountain, oak_tree, dinosaur