Dense object detectors rely on the sliding-window paradigm that predicts the object over a regular grid of image. Meanwhile, the feature maps on the point of the grid are adopted to generate the bounding box predictions. The point feature is convenient to use but may lack the explicit border information for accurate localization. In this paper, We propose a simple and efficient operator called Border-Align to extract "border features" from the extreme point of the border to enhance the point feature. Based on the BorderAlign, we design a novel detection architecture called BorderDet, which explicitly exploits the border information for stronger classification and more accurate localization. With ResNet-50 backbone, our method improves single-stage detector FCOS by 2.8 AP gains (38.6 v.s. 41.4). With the ResNeXt-101-DCN backbone, our BorderDet obtains 50.3 AP, outperforming the existing state-of-the-art approaches. The code is available at (https://github.com/Megvii-BaseDetection/BorderDet).
@article{arxiv.2007.11056,
title = {BorderDet: Border Feature for Dense Object Detection},
author = {Han Qiu and Yuchen Ma and Zeming Li and Songtao Liu and Jian Sun},
journal= {arXiv preprint arXiv:2007.11056},
year = {2021}
}
Comments
Accepted by ECCV 2020 as Oral. First two authors contributed equally