Estimated Depth Map Helps Image Classification

GitHub - yihui-he/Estimated-Depth-Map-Helps-Image-Classification: Depth estimation with neural network, and learning on RGBD images

You can't perform that action at this time. You signed in with another tab or window. You signed out in another tab or window. Reload to refresh your session. Reload to refresh your session.

https://github.com/yihui-he/Estimated-Depth-Map-Helps-Image-Classification

Estimated Depth Map Helps Image Classification

We consider image classification with estimated depth. This problem falls into the domain of transfer learning, since we are using a model trained on a set of depth images to generate depth maps (additional features) for use in another classification problem using another disjoint set of images.

https://arxiv.org/abs/1709.07077

@article{estimated2017he,
  title={Estimated Depth Map Helps Image Classification},
  author={He, Yihui},
  journal={arXiv preprint arXiv:1709.07077},
  year={2017}
}

how to test

1. you can run tryhere.ipynb to test performance on RGBD and RGB images.

2. you can do depth estimation in train/ folder

Approach

1. train a mapping map RGB to depth

2. convert cifar10 to images

3. convert RGBD to cifar10 format

4. train neural network on RGBD dataset

download

External Links