Objects as Points
Xingyi Zhou UT Austin Dequan Wang UC Berkeley Philipp Krähenbühl UT Austin
Abstract
Detection identifies objects as axis-aligned boxes in an image. Most successful object detectors enumerate a nearly exhaustive list of potential object locations and classify each. This is wasteful, inefficient, and requires additional post-processing. In this paper, we take a different approach. We model an object as a single point — the center point of its bounding box. Our detector uses keypoint estimation to find center points and regresses to all other object properties, such as size, 3D location, orientation, and even pose. Our center point based approach, CenterNet, is end-to-end differentiable, simpler, faster, and more accurate than corresponding bounding box based detectors. CenterNet achieves the best speed-accuracy trade-off on the MS COCO dataset, with $28.1\%$ AP at 142 FPS, $37.4\%$ AP at 52 FPS, and $45.1\%$ AP with multi-scale testing at 1.4 FPS. We use the same approach to estimate 3D bounding box in the KITTI benchmark and human pose on the COCO keypoint dataset. Our method performs competitively with sophisticated multi-stage methods and runs in real-time.
中文速览
目标检测领域长期依赖密集枚举候选框再筛选的思路，不仅计算浪费，还需要繁琐的非极大值抑制后处理。CenterNet 提出把每个目标表示为边界框的中心点，用关键点热力图（keypoint heatmap）直接定位中心，再从该点回归出目标的尺寸、3D位置、朝向乃至人体姿态，整个流程一次前向传播即可完成，无需后处理。在 MS COCO 数据集上，CenterNet 以142 FPS 实现28.1% AP、52 FPS 实现37.4% AP，速度-精度权衡全面优于同类检测器，并在3D目标检测和人体姿态估计任务上同样达到有竞争力的水平。这项工作的价值在于它将目标检测彻底简化为关键点估计，框架足够通用，只需为中心点附加不同的回归头便能扩展到多种视觉任务，为后续anchor-free检测研究奠定了重要基础。
原文 arXiv:1904.07850;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1904.07850v2