Reinforcement Learning for Improving Object Detection
Abstract
The performance of a trained object detection neural network depends a lot on the image quality. Generally, images are pre-processed before feeding them into the neural network and domain knowledge about the image dataset is used to choose the pre-processing techniques. In this paper, we introduce an algorithm called ObjectRL to choose the amount of a particular pre-processing to be applied to improve the object detection performances of pre-trained networks. The main motivation for ObjectRL is that an image which looks good to a human eye may not necessarily be the optimal one for a pre-trained object detector to detect objects.
Cite
Text
Nayak and Ravindran. "Reinforcement Learning for Improving Object Detection." European Conference on Computer Vision Workshops, 2020. doi:10.1007/978-3-030-68238-5_12Markdown
[Nayak and Ravindran. "Reinforcement Learning for Improving Object Detection." European Conference on Computer Vision Workshops, 2020.](https://mlanthology.org/eccvw/2020/nayak2020eccvw-reinforcement/) doi:10.1007/978-3-030-68238-5_12BibTeX
@inproceedings{nayak2020eccvw-reinforcement,
title = {{Reinforcement Learning for Improving Object Detection}},
author = {Nayak, Siddharth and Ravindran, Balaraman},
booktitle = {European Conference on Computer Vision Workshops},
year = {2020},
pages = {149-161},
doi = {10.1007/978-3-030-68238-5_12},
url = {https://mlanthology.org/eccvw/2020/nayak2020eccvw-reinforcement/}
}