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
Curvature-Driven Deformable Convolutional Networks for End-To-End Object Detection
Xiao-Ya Gu,Ying Fu +1 more
TL;DR:
Journal ArticleDOI
YOLO-A2G: An air-to-ground high-precision object detection algorithm based on YOLOv5
TL;DR: An improved air-to-ground object detection algorithm, YOLO-A2G, is proposed to solve the problem of insufficient number of battlefield samples in air- to-ground imaging, many ground background disturbances and large-scale variation and, in the post-processing stage after the network prediction, used Weighted Boxes Fusion instead of the traditional NMS to achieve spatial scale fusion.
Book ChapterDOI
A Handwritten Text Detection Model Based on Cascade Feature Fusion Network Improved by FCOS
TL;DR: Wang et al. as mentioned in this paper proposed a method for detecting handwritten ancient texts based on cascade feature fusion, which aims to improve the fusion of localization information in lower layers, and incorporate skip connections to better extract information in the backbone.
Book ChapterDOI
Applying of Adaptive Threshold Non-maximum Suppression to Pneumonia Detection
TL;DR: An adaptive threshold NMS that uses different thresholds to suppress the bounding boxes whose overlaps are not significant is proposed that provides improvements on Faster R-CNN with the AP metric on pneumonia dataset.
Journal ArticleDOI
Deep Transfer Learning Based Multiway Feature Pyramid Network for Object Detection in Images
TL;DR: This paper proposes a method for object detection in digital images that is more accurate and faster based on Single-Stage Multibox Detector (SSD) architecture and shows better detection quality in terms of mean Average Precision (mAP).
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.