| Autor: |
Shepley AJ, Falzon G, Kwan P, Brankovic L |
| Jazyk: |
angličtina |
| Zdroj: |
IEEE transactions on pattern analysis and machine intelligence [IEEE Trans Pattern Anal Mach Intell] 2023 Oct; Vol. 45 (10), pp. 11561-11574. Date of Electronic Publication: 2023 Sep 05. |
| DOI: |
10.1109/TPAMI.2023.3273210 |
| Abstrakt: |
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. |
| Databáze: |
MEDLINE |
| Externí odkaz: |
|
