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.
翻译:在物体探测中,它克服了基于 IoU 的 NMS 变量的内在限制,通过使用正常的曼哈顿远程激发的近距离指标来提供一个更稳定、更一致的捆绑箱群预测器,以代表捆绑箱群。与贪婪和软NMS不同的是,它不单单依靠分类信任分数来选择最佳捆绑箱,而是选择与特定组群中每个其它框体最接近的框,并去除高度兼容的相邻箱。 影响是对MS COCO和众人基准的试验性验证,提高了平均精度,提高了2.3-3.8%,平均回调了5.3-7.2%,而相对于脱法标准以及艺术NMS 变量的状态。 量化结果得到了广泛的质量分析和临界敏感度分析实验的支持,支持这一结论,即Covication比NMS 变异体更坚固。 影响代表了捆绑箱处理的范式转变,有可能取代IOU 绑框的回归过程。