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
Traffic perception from aerial images using butterfly fields
TL;DR: In this paper , an anchor-free method that leverages field-based representations is proposed to detect objects in aerial images, called butterfly detector, which employs a voting mechanism between related Butterfly vectors pointing to the object center.
Proceedings ArticleDOI
Two-stage Airplane Detection with NMS Filtering in Remote Sensing Images
Yucheng Song,Jinwen Tian +1 more
TL;DR: The method is able to accomplish the task in remote sensing for the detection and recognition of airplanes in 24 different classes including helicopter and wing aircrafts, and the NMS postprocessing would have a positive influence on improving the recall and mean average precision (mAP) metrics.
Proceedings ArticleDOI
Action-aware Masking Network with Group-based Attention for Temporal Action Localization
TL;DR: Wang et al. as discussed by the authors proposed an Action-aware Masking Network (AMNet), which simultaneously refines video features using action-aware attention and considers inherent temporal relations using self-attention and cross-att attention mechanisms.
Proceedings ArticleDOI
Eye-Net: An Interpretable Machine Learning Ensemble for Feature Engineering, Classification, and Lesion Localization of Diabetic Retinopathy
Justin Liu,Jorge Cuadros +1 more
TL;DR: In this article , a machine learning system was proposed to offer an efficient and accurate alternative that may automate diabetic retinopathy (DR) screening, which is particularly pervasive in developing countries, where there exists a severe deficiency of ophthalmologists.
Journal ArticleDOI
Scheme to implement moving target detection of coastal defense radar in complicated sea conditions
TL;DR: Wang et al. as mentioned in this paper used the ResNet50_FPN module as the backbone feature extractor to improve the detection performance of small-sized objects and selected the Softer-NMS algorithm to significantly improve the positioning accuracy through confidence estimation.
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.