Region anchors are the cornerstone of modern object detection techniques.
State-of-the-art detectors mostly rely on a dense anchoring scheme, where
anchors are sampled uniformly over the spatial domain with a predefined set of
scales and aspect ratios. In this paper, we revisit this foundational stage.
Our study shows that it can be done much more effectively and efficiently.
Specifically, we present an alternative scheme, named Guided Anchoring, which
leverages semantic features to guide the anchoring. The proposed method jointly
predicts the locations where the center of objects of interest are likely to
exist as well as the scales and aspect ratios at different locations. On top of
predicted anchor shapes, we mitigate the feature inconsistency with a feature
adaption module. We also study the use of high-quality proposals to improve
detection performance. The anchoring scheme can be seamlessly integrated into
proposal methods and detectors. With Guided Anchoring, we achieve 9.1% higher
recall on MS COCO with 90% fewer anchors than the RPN baseline. We also adopt
Guided Anchoring in Fast R-CNN, Faster R-CNN and RetinaNet, respectively
improving the detection mAP by 2.2%, 2.7% and 1.2%. Code will be available at
this https URL

本研究提出了一种名为 “Guided Anchoring” 的替代方案，该方案利用语义特征引导区域 anchor 的选择，并成功将其应用在目标检测和 Proposal 方法中，相比 RPN 基线，在 MS COCO 数据集上使用 “Guided Anchoring” 能够在减少 90% anchor 数量的情况下提高 9.1% 的召回率，同时在 Fast R-CNN、Faster R-CNN 和 RetinaNet 中将检测 mAP 分别提高了 2.2％、2.7％和 1.2％。