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
Target Detection Method of UAV Aerial Imagery Based on Improved YOLOv5
TL;DR: Improvements on the basis of YOLOv5l have been made, using asymmetric convolutions, and the backbone of the proposed method increased the top-one accuracy of the classification task by 7.20% on the CIFAR-10 dataset.
Journal ArticleDOI
Digital Twin of Intelligent Small Surface Defect Detection with Cyber-Manufacturing Systems
TL;DR: Wang et al. as mentioned in this paper constructed cyber-manufacturing systems to achieve a digital twin (DT) solution for small surface defect detection task, which consists of an Edge-Cloud architecture and a surface detection algorithm.
Proceedings ArticleDOI
MSNet: A Multilevel Instance Segmentation Network for Natural Disaster Damage Assessment in Aerial Videos
TL;DR: In this paper, the authors study the problem of efficiently assessing building damage after natural disasters like hurricanes, floods or fires, through aerial video analysis and propose a new model, namely MSNet, which contains novel region proposal network designs and an unsupervised score refinement network for confidence score calibration in both bounding box and mask branches.
Posted Content
Deep Regionlets: Blended Representation and Deep Learning for Generic Object Detection
TL;DR: This article proposes a novel object detection algorithm named ”Deep Regionlets” by integrating deep neural networks and a conventional detection schema for accurate generic object detection with competitive performance over state-of-the-art algorithms, such as RetinaNet and Mask R-CNN.
Journal ArticleDOI
COLOR: Cycling, Offline Learning, and Online Representation Framework for Airport and Airplane Detection Using GF-2 Satellite Images
TL;DR: A novel cycling data-driven framework for efficient and robust airport localization and airplane detection and the proposed method is much faster than the traditional approaches in real-world applications.
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.