论文标题
特征驱动的超级分辨率用于对象检测
Feature-Driven Super-Resolution for Object Detection
论文作者
论文摘要
尽管一些基于卷积神经网络（CNN）的超分辨率（SR）算法最近在单个图像上产生了良好的视觉性能。他们中的大多数专注于完美的感知质量，但忽略了后续检测任务的特定需求。本文提出了一个简单但功能强大的功能驱动的超分辨率（FDSR），以提高低分辨率（LR）图像的检测性能。首先，提出的方法使用特征域的先验，从现有检测器主链中提取以指导HR图像重建。然后，使用对齐功能，FDSR更新SR参数以获得更好的检测性能。与某些最先进的SR算法与4 $ \ times $ scale因子相比，FDSR优于MS Coco验证上的检测性能图，VOC2007数据库具有良好的概括为其他检测网络。
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$\times$ scale factor, FDSR outperforms the detection performance mAP on MS COCO validation, VOC2007 databases with good generalization to other detection networks.
