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
Construction site safety monitoring and excavator activity analysis system
TL;DR: Zhang et al. as discussed by the authors proposed a vision-based excavator perception, activity analysis, and safety monitoring system, which can detect multi-class construction machines and humans in real-time while estimating the poses and actions of the excavator.
Proceedings ArticleDOI
Intelligent unmanned aerial vehicle (UAV) system for aircraft surface inspection
TL;DR: Wang et al. as mentioned in this paper designed an unmanned aerial vehicle (UAV) intelligent system to collect aircraft surface images and used deep learning object detection algorithm to independently and efficiently solved aircraft surface inspection.
Journal ArticleDOI
Dual-View Single-Shot Multibox Detector at Urban Intersections: Settings and Performance Evaluation
TL;DR: In this article , a multi-camera video content analysis (VCA) system that exploits a single-shot multibox detector (SSD) network to detect vehicles, riders, and pedestrians and triggers alerts to drivers of public transportation vehicles approaching the surveilled area is presented.
Journal ArticleDOI
Temporal action detection with dynamic weights based on curriculum learning
TL;DR: Zhang et al. as mentioned in this paper designed a dynamic weighting strategy based on curriculum learning, where the weights of training samples are a combination of their classification and localization scores in different training stages.
Book ChapterDOI
An Improved Lightweight Network Based on YOLOv5s for Object Detection in Autonomous Driving
TL;DR: In this article , a lightweight object detection network based on YOLOv5s which is one of the most promising object detection networks in the current literature is proposed. But the proposed network is not suitable for real-time detection in autonomous driving.
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.