Union-over-Intersections：超越 Winner-Takes-All 的目标检测
Union-over-Intersections: Object Detection beyond Winner-Takes-All
AI总结：
提出Union-over-Intersections方法，通过仅回归提议与真实值的交集并取并集生成最终框，避免外推并利用多框信息，以即插即用方式提升多种检测架构的定位与分割精度。
摘要：
本文重新审视了目标检测架构中预测边界框位置的问题。通常，每个边界框提议或边界框查询旨在直接最大化与真实值的交并比分数，随后采用胜者通吃的非极大值抑制，仅保留每个区域中得分最高的边界框。我们观察到这两个步骤都是次优的：第一步涉及将提议回归到整个真实值，即使具有大感受野这也是一项困难的任务；第二步忽略了除最高候选框之外其他边界框的有价值信息。我们不将提议回归到整个真实值，而是提出一种更简单的方法：仅回归到提议与真实值之间的交集区域。这避免了提议在其视觉范围之外进行外推的需要，从而提高了定位精度。我们不采用胜者通吃策略，而是对一个区域内所有边界框的回归交集取并集，以生成最终的边界框输出。我们的即插即用方法以最小的修改无缝集成到基于提议、基于网格和基于查询的检测架构中，持续改进了目标定位和实例分割。我们展示了其在各种检测和分割任务中的广泛适用性和多功能性。
英文摘要：
This paper revisits the problem of predicting box locations in object detection architectures. Typically, each box proposal or box query aims to directly maximize the intersection-over-union score with the ground truth, followed by a winner-takes-all non-maximum suppression where only the highest scoring box in each region is retained. We observe that both steps are sub-optimal: the first involves regressing proposals to the entire ground truth, which is a difficult task even with large receptive fields, and the second neglects valuable information from boxes other than the top candidate. Instead of regressing proposals to the whole ground truth, we propose a simpler approach: regress only to the area of intersection between the proposal and the ground truth. This avoids the need for proposals to extrapolate beyond their visual scope, improving localization accuracy. Rather than adopting a winner-takes-all strategy, we take the union over the regressed intersections of all boxes in a region to generate the final box outputs. Our plug-and-play method integrates seamlessly into proposal-based, grid-based, and query-based detection architectures with minimal modifications, consistently improving object localization and instance segmentation. We demonstrate its broad applicability and versatility across various detection and segmentation tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
