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
MaskFace: multi-task face and landmark detector
TL;DR: The method, called MaskFace, extends previous face detection approaches by adding a keypoint prediction head that adopts ideas of Mask R-CNN by extracting facial features with a RoIAlign layer and achieves state-of-the-art results outperforming many of single-task and multi-task models.
Proceedings ArticleDOI
Intrusion detection of foreign objects in high-voltage lines based on YOLOv4
TL;DR: In this article, a high-voltage line foreign object intrusion detection model based on Yolov4 was proposed to provide early warning of the danger of foreign body intrusion around the transmission line.
Journal ArticleDOI
Two-Stream RGB-D Human Detection Algorithm Based on RFB Network
TL;DR: The experimental results show that the proposed two-stream RGB-D human detection algorithm based on RFB network has a significant improvement compared with other algorithms on two common datasets.
Posted Content
Towards Single-phase Single-stage Detection of Pulmonary Nodules in Chest CT Imaging
TL;DR: This work abandon the conventional two-phase paradigm and two-stage framework altogether and propose to train a single network for end-to-end nodule detection instead, without transfer learning or further post-processing, which substantially outperforms prior art in terms of both accuracy and speed.
Proceedings ArticleDOI
Lightdet: A Lightweight and Accurate Object Detection Network
TL;DR: A lightweight backbone that is able to capture rich low-level features by the proposed Detail-Preserving Module to effectively aggregate bottom and top-down features, and introduces an efficient Feature- Preserving and Refinement Module to further reduce the entire network complexity.
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.