Corpus ID: 231861485

Improving Aerial Instance Segmentation in the Dark with Self-Supervised Low Light Enhancement

@article{Garg2021ImprovingAI,
  title={Improving Aerial Instance Segmentation in the Dark with Self-Supervised Low Light Enhancement},
  author={Prateek Garg and Murari Mandal and Pratik Narang},
  journal={ArXiv},
  year={2021},
  volume={abs/2102.05399}
}
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… Expand

Figures and Tables from this paper

References

SHOWING 1-5 OF 5 REFERENCES
Deep Retinex Decomposition for Low-Light Enhancement
TLDR
Extensive experiments demonstrate that the proposed deep Retinex-Net learned on this LOw-Light dataset not only achieves visually pleasing quality for low-light enhancement but also provides a good representation of image decomposition. Expand
Self-supervised Image Enhancement Network: Training with Low Light Images Only
TLDR
It can be proved through experiments that the proposed method has reached the state-of-the-art in terms of processing speed and effect. Expand
iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images
TLDR
This work introduces the first benchmark dataset for instance segmentation in aerial imagery that combines instance-level object detection and pixel-level segmentation tasks, and introduces a large-scale and densely annotated Instance Segmentation in Aerial Images Dataset (iSAID). Expand
Hybrid Task Cascade for Instance Segmentation
TLDR
This work proposes a new framework, Hybrid Task Cascade (HTC), which differs in two important aspects: (1) instead of performing cascaded refinement on these two tasks separately, it interweaves them for a joint multi-stage processing; (2) it adopts a fully convolutional branch to provide spatial context, which can help distinguishing hard foreground from cluttered background. Expand