TY - JOUR AU - Garg, Prateek AU - Mandal, Murari AU - Narang, Pratik PY - 2021/05/18 Y2 - 2024/03/28 TI - Improving Aerial Instance Segmentation in the Dark with Self-Supervised Low Light Enhancement (Student Abstract) JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 35 IS - 18 SE - AAAI Student Abstract and Poster Program DO - 10.1609/aaai.v35i18.17887 UR - https://ojs.aaai.org/index.php/AAAI/article/view/17887 SP - 15781-15782 AB - Low light conditions in aerial images adversely affect the performance of several vision based applications. There is a need for methods that can efficiently remove the low light attributes and assist in the performance of key vision tasks. In this work, we propose a new method that is capable of enhancing the low light image in a self-supervised fashion, and sequentially apply detection and segmentation tasks in an end-to-end manner. The proposed method occupies a very small overhead in terms of memory and computational power over the original algorithm and delivers superior results. Additionally, we propose the generation of a new low light aerial dataset using GANs, which can be used to evaluate vision based networks for similar adverse conditions. ER -