作者：Chenhongyi Yang，Zehao Huang，Naiyan Wang
作者单位：University of Edinburgh（爱丁堡大学），TuSimple（图森未来，是一个无人驾驶卡车品牌）
发布时间：2021
发布期刊：Arxiv
论文全称：QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection
论文地址：https://arxiv.org/abs/2103.09136
论文代码：https://hub.fastgit.xyz/ChenhongyiYang/QueryDet-PyTorch
地位：
While general object detection with deep learning has achieved great success in the past few years, the performance and effificiency of detecting small objects are far from satisfactory. The most common and effective way to promote small object detection is to use high-resolution images or feature maps. However, both approaches induce costly computation since the computational cost grows squarely as the size of images and features increases. To get the best of two worlds, we propose QueryDet that uses a novel query mechanism to accelerate the inference speed of feature-pyramid based object detectors. The pipeline composes two steps: it fifirst predicts the coarse locations of small objects on low-resolution features and then computes the accurate detection results using high resolution features sparsely guided by those coarse positions. In this way, we can not only harvest the benefifit of high-resolution feature maps but also avoid useless computation for the background area. On the popular COCO dataset, the proposed method improves the detection mAP by 1.0 and mAP-small by 2.0, and the high resolution inference speed is improved to 3.0× on average.On VisDrone dataset, which contains more small objects,we create a new state-of-the-art while gaining a 2.3× high resolution acceleration on average