papers AI Learner
The Github is limit! Click to go to the new site.

Task-Driven Super Resolution: Object Detection in Low-resolution Images

2018-03-30
Muhammad Haris, Greg Shakhnarovich, Norimichi Ukita

Abstract

We consider how image super resolution (SR) can contribute to an object detection task in low-resolution images. Intuitively, SR gives a positive impact on the object detection task. While several previous works demonstrated that this intuition is correct, SR and detector are optimized independently in these works. This paper proposes a novel framework to train a deep neural network where the SR sub-network explicitly incorporates a detection loss in its training objective, via a tradeoff with a traditional detection loss. This end-to-end training procedure allows us to train SR preprocessing for any differentiable detector. We demonstrate that our task-driven SR consistently and significantly improves accuracy of an object detector on low-resolution images for a variety of conditions and scaling factors.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1803.11316

PDF

https://arxiv.org/pdf/1803.11316


Similar Posts

Comments