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
Posted Content
Joint Object Contour Points and Semantics for Instance Segmentation
Wen chao Zhang,Chong Fu,Mai Zhu +2 more
TL;DR: Wang et al. as discussed by the authors propose Mask Point R-CNN, which aims at promoting the neural network's attention to the object boundary by adding a contour point detection auxiliary task.
Proceedings ArticleDOI
CSL-YOLO: A Cross-Stage Lightweight Object Detector with Low FLOPs
TL;DR: In this article , the authors proposed a new lightweight convolution method Cross-Stage Lightweight Module (CSL-M), which combines the Inverted residual block (IRB) and cross-stage Partial (CSP) concept.
Proceedings ArticleDOI
Research on Vision-Based Object Detection Algorithm for Marine Obstacles
TL;DR: In this article , a target detection algorithm for multiple types of obstacles based on visual images is proposed, which can be quickly implemented on the graphics processing unit (GPU), which can achieve approximately real-time image processing.
Journal ArticleDOI
Identification of wormholes in soybean leaves based on multi-feature structure and attention mechanism
WenBo Fang,Fachun Guan,Helong Yu,Chunguang Bi,Yonggang Guo,Yanru Cui,Li Su,Zhengchao Zhang,Jiao Xie +8 more
Journal ArticleDOI
Temporal Context Modeling Network with Local-Global Complementary Architecture for Temporal Proposal Generation
TL;DR: TCMNet as mentioned in this paper proposes a unified framework named Temporal Context Modeling Network (TCMnet) that generates temporal action proposals by using convolutional filters with different dilation rates to address the temporal scale issue.
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.