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
An improved object detection algorithm based on multi-scaled and deformable convolutional neural networks
Danyang Cao,Zhixin Chen,Gao Lei +2 more
TL;DR: This study compares and analyse mainstream object detection algorithms and proposes a multi-scaled deformable convolutional object detection network to deal with the challenges faced by current methods and demonstrates a strong performance on par, or even better, than state of the art methods.
Journal ArticleDOI
DA-Net: Learning the Fine-Grained Density Distribution With Deformation Aggregation Network
TL;DR: The deformation aggregation network (DA-Net) is proposed that can incrementally incorporate adaptive receptive fields to capture the fine-grained density distribution and delivers the state-of-the-art performance on four benchmarks.
Posted Content
Deep Learning in Diabetic Foot Ulcers Detection: A Comprehensive Evaluation
Moi Hoon Yap,Ryo Hachiuma,Azadeh Alavi,Raphael Brüngel,Bill Cassidy,Manu Goyal,Hongtao Zhu,Johannes Rückert,Moshe Olshansky,Xiao Huang,Hideo Saito,Saeed Hassanpour,Christoph M. Friedrich,David B. Ascher,Anping Song,Hiroki Kajita,David Gillespie,Neil D. Reeves,Joseph M Pappachan,Claire O'Shea,Eibe Frank +20 more
TL;DR: This paper summarizes the results of DFUC2020 by comparing the deep learning-based algorithms proposed by the winning teams: Faster R-CNN, three variants of FasterR-CNN and an ensemble method; YOLOv3; Y OLOv5; EfficientDet; and a new Cascade Attention Network.
Journal Article
A Novel CNN-based Method for Accurate Ship Detection in HR Optical Remote Sensing Images via Rotated Bounding Box
TL;DR: A novel CNN-based ship detection method that is able to predict the orientation and other variables independently, and yet more effectively, with a novel dual-branch regression network, based on the observation that the ship targets are nearly rotation-invariant in remote sensing images.
Journal ArticleDOI
A Method for Vehicle Detection in High-Resolution Satellite Images that Uses a Region-Based Object Detector and Unsupervised Domain Adaptation
TL;DR: This work proposed an unsupervised domain adaptation (DA) method that does not require labeled training data, and thus can maintain detection performance in the target domain at a low cost, and improved adversarial DA by utilizing the reconstruction loss to facilitate learning semantic features.
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.