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

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

1 Dec 2020arXiv:2012.00257archive 2025-07-28

Andrew Shepley, Greg Falzon, Paul Kwan

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.

Paper PDF Code

Code

ashep29/confluence officialmentioned in papermentioned on GitHub report

Huangdebo/Confluence mentioned on GitHubpytorch report

lmk123568/OD_Confluence mentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Clustering Object Detection object-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 Convolution Average Pooling Batch Normalization Convolution FPN Focal Loss Global Average Pooling Logistic Regression Residual Connection RetinaNet Softmax YOLOv3 k-Means Clustering

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections