Confluence: A Robust Non-IoU Alternative to Non-Maxima Suppression in Object Detection

Author(s)
Shepley, Andrew J
Falzon, Gregory
Kwan, Paul
Brankovic, Ljiljana
Publication Date
2023-05-05
Abstract
<p>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 0.2--2.7% and 1--3.8% respectively and Average Recall by 1.3--9.3 and 2.4--7.3% when compared against Greedy and Soft-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.</p>
Citation
IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(10), p. 11561-11574
ISSN
0162-8828
Link
Publisher
IEEE
Title
Confluence: A Robust Non-IoU Alternative to Non-Maxima Suppression in Object Detection
Type of document
Journal Article
Entity Type
Publication

Files:

NameSizeformatDescriptionLink