# Feature-Driven Super-Resolution for Object Detection

arXiv: https://arxiv.org/abs/2004.00554 · HTML: https://mlsanity.com/paper/2004.00554/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Apr 2020.

## Built on by (most cited first, 1 of 1)

- [Can Super Resolution be used to improve Human Pose Estimation in Low Resolution Scenarios?](https://mlsanity.com/paper/2107.02108/) (2021)

## Abstract (arXiv)

Although some convolutional neural networks (CNNs) based super-resolution (SR) algorithms yield good visual performances on single images recently. Most of them focus on perfect perceptual quality but ignore specific needs of subsequent detection task. This paper proposes a simple but powerful feature-driven super-resolution (FDSR) to improve the detection performance of low-resolution (LR) images. First, the proposed method uses feature-domain prior which extracts from an existing detector backbone to guide the HR image reconstruction. Then, with the aligned features, FDSR update SR parameters for better detection performance. Comparing with some state-of-the-art SR algorithms with 4× scale factor, FDSR outperforms the detection performance mAP on MS COCO validation, VOC2007 databases with good generalization to other detection networks.