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
Deep learning for detection and segmentation of artefact and disease instances in gastrointestinal endoscopy.
Sharib Ali,Mariia Dmitrieva,Noha M. Ghatwary,Sophia Bano,Gorkem Polat,Alptekin Temizel,Adrian Krenzer,Amar Hekalo,Yun Bo Guo,Bogdan J. Matuszewski,Mourad Gridach,Irina Voiculescu,Vishnusai Yoganand,Arnav Chavan,Aryan Raj,Nhan Trung Nguyen,Dat Q. Tran,Lê Duy Huynh,Nicolas Boutry,Shahadate Rezvy,Haijian Chen,Yoon-Ho Choi,Anand Subramanian,Velmurugan Balasubramanian,Xiaohong W. Gao,Hongyu Hu,Yusheng Liao,Danail Stoyanov,Christian Daul,Stefano Realdon,Renato Cannizzaro,Dominique Lamarque,Terry Tran-Nguyen,Adam A. Bailey,Barbara Braden,James E. East,Jens Rittscher +36 more
TL;DR: The Endoscopy Computer Vision Challenge (EndoCV) as discussed by the authors is a crowd-sourcing initiative to address eminent problems in developing reliable computer aided detection and diagnosis endoscopy systems and suggest a pathway for clinical translation of technologies.
Proceedings ArticleDOI
VisDrone-DET2019: The Vision Meets Drone Object Detection in Image Challenge Results
Dawei Du,Yue Zhang,Zexin Wang,Zhikang Wang,Zichen Song,Ziming Liu,Liefeng Bo,Hailin Shi,Rui Zhu,Aashish Kumar,Aijin Li,Almaz Zinollayev,Anuar Askergaliyev,Arne Schumann,Binjie Mao,Pengfei Zhu,Byeongwon Lee,Chang Liu,Changrui Chen,Chunhong Pan,Chunlei Huo,Da Yu,DeChun Cong,Dening Zeng,Dheeraj Reddy Pailla,Di Li,Longyin Wen,Dong Wang,Donghyeon Cho,Dongyu Zhang,Furui Bai,George Jose,Guangyu Gao,Guizhong Liu,Haitao Xiong,Hao Qi,Haoran Wang,Xiao Bian,Heqian Qiu,Hongliang Li,Huchuan Lu,Ildoo Kim,Jaekyum Kim,Jane Shen,Jihoon Lee,Jing Ge,Jingjing Xu,Jingkai Zhou,Haibin Lin,Jonas Meier,Jun Won Choi,Junhao Hu,Junyi Zhang,Junying Huang,Kaiqi Huang,Keyang Wang,Lars Sommer,Lei Jin,Lei Zhang,Qinghua Hu,Lianghua Huang,Lin Sun,Lucas Steinmann,Meixia Jia,Nuo Xu,Pengyi Zhang,Qiang Chen,Qingxuan Lv,Qiong Liu,Qishang Cheng,Tao Peng,Sai Saketh Chennamsetty,Shuhao Chen,Shuo Wei,Srinivas S S Kruthiventi,Sungeun Hong,Sungil Kang,Tong Wu,Tuo Feng,Varghese Alex Kollerathu,Wanqi Li,Jiayu Zheng,Wei Dai,Weida Qin,Weiyang Wang,Xiaorui Wang,Xiaoyu Chen,Xin Chen,Xin Sun,Xin Zhang,Xin Zhao,Xindi Zhang,Xinyao Wang,Xinyu Zhang,Xuankun Chen,Xudong Wei,Xuzhang Zhang,Yanchao Li,Yifu Chen,Yu Heng Toh,Yu Zhang,Yu Zhu,Yunxin Zhong +102 more
TL;DR: The Vision Meets Drone Object Detection in Image Challenge (VME-DET 2019) as discussed by the authors, held in conjunction with the 17th International Conference on Computer Vision (ICCV 2019), focuses on image object detection on drones.
Book ChapterDOI
Corner Proposal Network for Anchor-Free, Two-Stage Object Detection
TL;DR: CPNDet as discussed by the authors proposes a two-stage framework which first extracts a number of object proposals by finding potential corner keypoint combinations and then assigns a class label to each proposal by a standalone classification stage.
Journal ArticleDOI
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: In this paper, the authors compared the performance of state-of-the-art deep learning object detection frameworks applied to the detection and recognition of diabetic foot ulcers (DFUs).
Posted Content
Soft Sampling for Robust Object Detection
TL;DR: In this article, the authors study the robustness of object detection under the presence of missing annotations and propose a simple yet effective solution, called Soft Sampling, which re-weights the gradients of RoIs as a function of overlap with positive instances.
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.