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
A deep neural network method for analyzing the CMS High Granularity Calorimeter (HGCAL) events
TL;DR: The Mask R-CNN model which has already proven its efficiency in Industry (for 2D images) is presented, and the plans to extend it to tackle 3D HGCAL data are presented.
Journal ArticleDOI
Earf-YOLO: An Efficient Attention Receptive Field Model for Recognizing Symbols of Zhuang Minority Patterns
Xin Wang,Jingke Yan,Qin Qin,Qin Wang,Jingye Cai,Jianhua Deng,Jun Wang,Zhuo Shi,Yingying Feng,Bin Chen +9 more
TL;DR: The efficient attention receptive field you only look once (Earf-YOLO) is presented, a new scheme to address problems of recognizing Zhuang minority pattern symbols and comparative experiments indicate that the AP and FPS of the suggested model reach their highest values, manifesting its high efficiency.
Journal ArticleDOI
Pedestrian detection using multi-scale squeeze-and-excitation module
TL;DR: A deep learning-based pedestrian detection method for small and overlapping objects that adopts a parallel feature pyramid network with multi- Scale feature layers, and the multi-scale squeeze-and-excitation module is proposed for better selection of multi- scale features.
Posted Content
Smart-Inspect: Micro Scale Localization and Classification of Smartphone Glass Defects for Industrial Automation
TL;DR: A robust semi-supervised learning framework for intelligent micro-scaled localization and classification of defects on a 16K pixel image of smartphone glass that outperforms manual inspection in testing the quality of glass screen samples by identifying defects on samples that have been marked as good by human inspection.
Evaluation of different methods to measure a stent's pitch length in an industrial environment
TL;DR: In this article, the authors evaluated multiple approaches to measure a single pitch length using images in an industrial environment and concluded that the approach with the lowest error is the one with the smallest error.
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.