论文标题
汇合：在对象检测中，可鲁棒的非替代品替代非马克西马抑制
Confluence: A Robust Non-IoU Alternative to Non-Maxima Suppression in Object Detection
论文作者
论文摘要
Confluence是对偶数检测的边界盒后处理中非墨西哥抑制（NMS）替代的新型非交流（IOU）替代方案。它克服了基于IOU的NMS变体的固有局限性，以通过使用归一化的曼哈顿距离启发的接近度度量来表示边界框聚类的更稳定，一致的预测指标来表示边界框群集。与贪婪和柔软的NMS不同，它不仅依赖分类置信度得分来选择最佳边界框，而是选择与给定群集中最接近其他盒子的框并删除高度汇合的相邻框。在MS Coco和CrowdHuman基准测试中，汇合的平均精度最高为2.3-3.8％，而平均召回率则提高了5.3-7.2％，而与事实上的标准和ART NMS NMS变体相比。广泛的定性分析和阈值灵敏度分析实验支持了定量结果，这支持了结论比NMS变体更强大的结论。 Confluence代表边界框处理中的范式变化，有可能在边界框回归过程中替换IOU。
Confluence is a novel non-Intersection over Union (IoU) alternative to Non-Maxima Suppression (NMS) in bounding box post-processing in object detection. It overcomes the inherent limitations of IoU-based NMS variants to provide a more stable, consistent predictor of bounding box clustering by using a normalized Manhattan Distance inspired proximity metric to represent bounding box clustering. Unlike Greedy and Soft NMS, it does not rely solely on classification confidence scores to select optimal bounding boxes, instead selecting the box which is closest to every other box within a given cluster and removing highly confluent neighboring boxes. Confluence is experimentally validated on the MS COCO and CrowdHuman benchmarks, improving Average Precision by up to 2.3-3.8% and Average Recall by up to 5.3-7.2% when compared against de-facto standard and state of the art NMS variants. Quantitative results are supported by extensive qualitative analysis and threshold sensitivity analysis experiments support the conclusion that Confluence is more robust than NMS variants. Confluence represents a paradigm shift in bounding box processing, with potential to replace IoU in bounding box regression processes.
