Soft-NMS — Improving Object Detection with One Line of Code

@article{Bodla2017SoftNMSI,
  title={Soft-NMS — Improving Object Detection with One Line of Code},
  author={Navaneeth Bodla and Bharat Singh and Rama Chellappa and Larry S. Davis},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={5562-5570}
}
Non-maximum suppression is an integral part of the object detection pipeline. First, it sorts all detection boxes on the basis of their scores. The detection box M with the maximum score is selected and all other detection boxes with a significant overlap (using a pre-defined threshold) with M are suppressed. This process is recursively applied on the remaining boxes. As per the design of the algorithm, if an object lies within the predefined overlap threshold, it leads to a miss. To this end… CONTINUE READING

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • Using Deformable-RFCN, Soft-NMS improves state-of-the-art in object detection from 39.8% to 40.9% with a single model.

Citations

Publications citing this paper.
SHOWING 1-10 OF 134 CITATIONS

A Novel Effectively Optimized One-Stage Network for Object Detection in Remote Sensing Imagery

Weiying Xie, Haonan Qin, Yunsong Li, Zhuo Wang, Jie Lei
  • Remote Sensing
  • 2019
VIEW 11 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

A Unified Framework for Fault Detection of Freight Train Images Under Complex Environment

  • 2018 25th IEEE International Conference on Image Processing (ICIP)
  • 2018
VIEW 6 EXCERPTS
HIGHLY INFLUENCED

Inshore Ship Detection Based on Mask R-CNN

  • IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium
  • 2018
VIEW 11 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FoxNet: A Multi-face Alignment Method

  • ArXiv
  • 2019
VIEW 7 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

HAR-Net: Joint Learning of Hybrid Attention for Single-stage Object Detection

VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2017
2019

CITATION STATISTICS

  • 47 Highly Influenced Citations

  • Averaged 45 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 31 REFERENCES

Microsoft COCO: Common Objects in Context

VIEW 14 EXCERPTS
HIGHLY INFLUENTIAL

The Pascal Visual Object Classes (VOC) Challenge

VIEW 12 EXCERPTS
HIGHLY INFLUENTIAL

SSD: Single Shot MultiBox Detector

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2015
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

You Only Look Once: Unified, Real-Time Object Detection

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Optimized Pedestrian Detection for Multiple and Occluded People

  • 2013 IEEE Conference on Computer Vision and Pattern Recognition
  • 2013
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Deformable Convolutional Networks

  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Object retrieval with large vocabularies and fast spatial matching

  • 2007 IEEE Conference on Computer Vision and Pattern Recognition
  • 2007
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL