Soft-NMS — Improving Object Detection with One Line of Code
Navaneeth Bodla,Bharat Singh,Rama Chellappa,Larry S. Davis +3 more
- pp 5562-5570
TLDR
Soft-NMS as mentioned in this paper decays the detection scores of all other objects as a continuous function of their overlap with M. As per the design of the algorithm, if an object lies within the predefined overlap threshold, it leads to a miss.Abstract:
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, we propose Soft-NMS, an algorithm which decays the detection scores of all other objects as a continuous function of their overlap with M. Hence, no object is eliminated in this process. Soft-NMS obtains consistent improvements for the coco-style mAP metric on standard datasets like PASCAL VOC2007 (1.7% for both R-FCN and Faster-RCNN) and MS-COCO (1.3% for R-FCN and 1.1% for Faster-RCNN) by just changing the NMS algorithm without any additional hyper-parameters. Using Deformable-RFCN, Soft-NMS improves state-of-the-art in object detection from 39.8% to 40.9% with a single model. Further, the computational complexity of Soft-NMS is the same as traditional NMS and hence it can be efficiently implemented. Since Soft-NMS does not require any extra training and is simple to implement, it can be easily integrated into any object detection pipeline. Code for Soft-NMS is publicly available on GitHub http://bit.ly/2nJLNMu.read more
Citations
More filters
Journal ArticleDOI
WDN: A One-Stage Detection Network for Wheat Heads with High Performance
TL;DR: Based on the one-stage network framework, the wheat detection net (WDN) model was proposed for wheat head detection and counting as mentioned in this paper , where an attention module and feature fusion module were added to the backbone network and the formula for the loss function was optimized as well.
Proceedings ArticleDOI
Simple Pair Pose - Pairwise Human Pose Estimation in Dense Urban Traffic Scenes
TL;DR: In this article, a top-down method was proposed to estimate the two poses of pedestrians in a single forward pass within a deep convolutional neural network for dense urban traffic scenarios.
Proceedings ArticleDOI
Robust Object Detection Fusion Against Deception
Ka-Ho Chow,Ling Liu +1 more
TL;DR: FUSE as mentioned in this paper is a deception-resilient detection fusion approach with three novel contributions: diversityenhanced fusion teaming mechanisms, including diversity-enhanced joint training algorithms, for producing high diversity fusion detectors, and a three-tier detection fusion framework and a graph partitioning algorithm to construct fusion-verified detection outputs through three mutually reinforcing components.
Journal ArticleDOI
A line-segment-based non-maximum suppression method for accurate object detection
TL;DR: Zhang et al. as mentioned in this paper utilized the distribution of line segments to facilitate the Non-Maximum Suppression (NMS) for the object detection models and designed multiple differentiated metrics for the overlap measure between bounding boxes.
Book ChapterDOI
Fast Hand Detection in Collaborative Learning Environments.
Sravani Teeparthi,Venkatesh Jatla,Marios S. Pattichis,Sylvia Celedón-Pattichis,Carlos LopezLeiva +4 more
TL;DR: In this paper, the authors develop long-term hand detection methods that can deal with partial occlusions and dramatic changes in appearance for non-deformable objects in collaborative learning environments.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings ArticleDOI
Histograms of oriented gradients for human detection
Navneet Dalal,Bill Triggs +1 more
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.
Journal ArticleDOI
A Computational Approach to Edge Detection
TL;DR: There is a natural uncertainty principle between detection and localization performance, which are the two main goals, and with this principle a single operator shape is derived which is optimal at any scale.
Proceedings ArticleDOI
You Only Look Once: Unified, Real-Time Object Detection
TL;DR: Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
Proceedings ArticleDOI
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TL;DR: RCNN as discussed by the authors combines CNNs with bottom-up region proposals to localize and segment objects, and when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost.