Recently, one-stage object detectors gain much attention due to their
simplicity in practice. Its fully convolutional nature greatly reduces the
difficulty of training and deployment compared with two-stage detectors which
require NMS and sorting for the proposal stage. However, a fundamental issue
lies in all one-stage detectors is the misalignment between anchor boxes and
convolutional features, which significantly hinders the performance of
one-stage detectors. In this work, we first reveal the deep connection between
the widely used im2col operator and the RoIAlign operator. Guided by this
illuminating observation, we propose a RoIConv operator which aligns the
features and its corresponding anchors in one-stage detection in a principled
way. We then design a fully convolutional AlignDet architecture which combines
the flexibility of learned anchors and the preciseness of aligned features.
Specifically, our AlignDet achieves a state-of-the-art mAP of 44.1 on the COCO
test-dev with ResNeXt-101 backbone.

提出了一种 RoIConv 算子和 AlignDet 架构，用于解决单阶段目标检测中 anchor boxes 和卷积特征之间的错位问题，取得了 44.1 的最佳平均精确度。