Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Methods/Soft-NMS

Soft-NMS

Computer VisionIntroduced 200022 papers

Description

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.

Soft-NMS solves this problem by decaying the detection scores of all other objects as a continuous function of their overlap with M. Hence, no object is eliminated in this process.

Papers Using This Method

Work-Efficient Parallel Non-Maximum Suppression Kernels2025-02-01 Underwater Soft Coral Detection: SCoralNet for Accurate and Efficient Annotation.2024-08-01 Detection Selection Algorithm: A Likelihood based Optimization Method to Perform Post Processing for Object Detection2022-12-12 Deep learning approaches to building rooftop thermal bridge detection from aerial images2022-12-12 An advanced YOLOv3 method for small object detection2022-12-06 NeighborTrack: Improving Single Object Tracking by Bipartite Matching with Neighbor Tracklets2022-11-12 MDS-Net: A Multi-scale Depth Stratification Based Monocular 3D Object Detection Algorithm2022-01-12 DRPN: Making CNN Dynamically Handle Scale Variation2021-12-21 Confidence Propagation Cluster: Unleash Full Potential of Object Detectors2021-12-01 Quantum-soft QUBO Suppression for Accurate Object Detection2020-07-28 HoughNet: Integrating near and long-range evidence for bottom-up object detection2020-07-05 Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training2020-04-13 1st Place Solutions for OpenImage2019 -- Object Detection and Instance Segmentation2020-03-17 MatrixNets: A New Scale and Aspect Ratio Aware Architecture for Object Detection2020-01-09 CornerNet-Lite: Efficient Keypoint Based Object Detection2019-04-18 CenterNet: Keypoint Triplets for Object Detection2019-04-17 ThunderNet: Towards Real-time Generic Object Detection2019-03-28 Bottom-up Object Detection by Grouping Extreme and Center Points2019-01-23 Hybrid Task Cascade for Instance Segmentation2019-01-22 Scale-Aware Trident Networks for Object Detection2019-01-07