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
Book ChapterDOI
Face Detection with Better Representation Using a Multi-region WR-Inception Network Model
TL;DR: A multi- Region WR-Inception network model for face detection based on the Faster RCNN framework is proposed, utilizing multi-region features to obtain better face representation and introducing block loss to enable the model to be robust to occluded faces.
Journal ArticleDOI
Review on Uncertainty Estimation in Deep-Learning-Based Environment Perception of Intelligent Vehicles
Book ChapterDOI
A Close Look at Multi-tenant Parallel CNN Inference for Autonomous Driving.
TL;DR: In this article, a multi-tenant parallel CNN inference framework, MPInfer, was developed to evaluate the performance of various parallel execution modes with different data transfer modes between CPU/GPU and GPU platforms.
Journal Article
Intelligent Robust Base-Station Research in Harsh Outdoor Wilderness Environments for Wildsense
Junho Ahn,Akshay Mysore,Kati Zybko,Caroline Krumm,Dohyeon Lee,Dahyeon Kim,Richard Han,Shivakant Mishra,Thompson Hobbs +8 more
TL;DR: In this paper, an intelligent robust base station research with a low-cost and time saving method to obtain recording sensor data from their collars to a listener node, and readings are obtained without opening the weatherproof deer collar.
P ix 2 seq : a l anguage m odeling f ramework for o bject d etection
TL;DR: Pix2Seq is presented, a simple and generic framework for object detection that achieves competitive results on the challenging COCO dataset, compared to highly specialized and well optimized detection algorithms.
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.