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
Occlusion Handling and Multi-Scale Pedestrian Detection Based on Deep Learning: A Review
TL;DR: A detailed review of recent progress in pedestrian detection and the popular datasets and evaluation methods for pedestrian detection focusing on occlusion and scale variance are introduced.
Journal ArticleDOI
An Efficient Feature Pyramid Network for Object Detection in Remote Sensing Imagery
TL;DR: A novel feature pyramid network with Adaptive Residual Spatial Bi-Fusion (ARSF) as a solution to scale diversity, small target, and power limitation in remote sensing imagery and two lightweight versions are validated for future research of online object detection on satellites in aerospace engineering.
Journal ArticleDOI
Feature Enhancement for Multi-scale Object Detection
Huicheng Zheng,Huicheng Zheng,Jiajie Chen,Lvran Chen,Lvran Chen,Ye Li,Ye Li,Zhiwei Yan,Zhiwei Yan +8 more
TL;DR: A feature enhancement method that constructs feature channels based on oriented gradients as input to convolutional neural networks to capture discriminative local orientations and demonstrates superiority of the proposed method compared with state-of-the-art methods for multi-scale object detection.
Posted Content
Detection in Crowded Scenes: One Proposal, Multiple Predictions
TL;DR: Zhang et al. as discussed by the authors proposed a simple yet effective proposal-based object detector, aiming at detecting highly-overlapped instances in crowded scenes, which can effectively handle the difficulty of detecting highly overlapped objects.
Journal ArticleDOI
Automated High-Resolution Earth Observation Image Interpretation: Outcome of the 2020 Gaofen Challenge
Xian Sun,Peijin Wang,Zhiyuan Yan,Wenhui Diao,Xiaonan Lu,Zhujun Yang,Yidan Zhang,Deliang Xiang,Chen Yan,Jie Guo,Bo Dang,Wei Wei,Feng Xu,Cheng Wang,Ronny Hänsch,Martin Weinmann,Naoto Yokoya,Kun Fu +17 more
TL;DR: The 2020 Gaofen Challenge as discussed by the authors is an international image interpretation challenge organized by the China High-Resolution Earth Observation Conference Committee and the Aerospace Information Research Institute, Chinese Academy of Sciences.
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.