论文标题
完全卷积网络的端到端对象检测
End-to-End Object Detection with Fully Convolutional Network
论文作者
论文摘要
基于完全卷积网络的主流对象探测器的性能令人印象深刻。尽管他们中的大多数仍然需要手工设计的非最大抑制（NMS）后处理，这阻碍了完全端到端的培训。在本文中，我们对丢弃NMS进行分析，其中结果表明适当的标签分配起着至关重要的作用。为此，对于完全卷积检测器，我们引入了一个预测意识到的一对一（POTO）标签分配以进行分类以实现端到端检测，该检测获得了与NMS相当的性能。此外，提出了简单的3D最大滤波（3DMF）来利用多尺度特征并提高局部区域中卷积的可区分性。借助这些技术，我们的端到端框架可以通过可可和人类数据集上的NMS来实现许多最先进的探测器的竞争性能。该代码可在https://github.com/megvii astection/defcn上获得。
Mainstream object detectors based on the fully convolutional network has achieved impressive performance. While most of them still need a hand-designed non-maximum suppression (NMS) post-processing, which impedes fully end-to-end training. In this paper, we give the analysis of discarding NMS, where the results reveal that a proper label assignment plays a crucial role. To this end, for fully convolutional detectors, we introduce a Prediction-aware One-To-One (POTO) label assignment for classification to enable end-to-end detection, which obtains comparable performance with NMS. Besides, a simple 3D Max Filtering (3DMF) is proposed to utilize the multi-scale features and improve the discriminability of convolutions in the local region. With these techniques, our end-to-end framework achieves competitive performance against many state-of-the-art detectors with NMS on COCO and CrowdHuman datasets. The code is available at https://github.com/Megvii-BaseDetection/DeFCN .
