Ensemble Methods for Object Detection

Object detection is one of the most important topics of computer vision since it has many applications in several fields. Object detection models can be improved thanks to ensemble techniques; however, the process of ensembling object detectors poses several challenges. In this paper, we present an ensemble algorithm that can be applied with any object detection model independently of the underlying algorithm. In addition, our ensemble method has been employed to define a test-time augmentation procedure for object detection models. Our ensemble algorithm and test-time augmentation procedure can be used to apply data and model distillation for object detection, two semi-supervised learning techniques that reduce the number of necessary annotated images to train a model. We have tested our methods with several datasets and algorithms, obtaining up to a 10% improvement from the base models. All the methods are implemented in an open-source library.

[1]  Kaiming He,et al.  Data Distillation: Towards Omni-Supervised Learning , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[2]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[3]  Weimin Wang,et al.  Weighted Boxes Fusion: ensembling boxes for object detection models , 2019, ArXiv.

[4]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[5]  Yuhui Zheng,et al.  Ensemble R-FCN for Object Detection , 2017, CSA/CUTE.

[6]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Bernt Schiele,et al.  Learning Non-maximum Suppression , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Quoc V. Le,et al.  Learning Data Augmentation Strategies for Object Detection , 2019, ECCV.

[9]  Robbie Waugh,et al.  Reducing Stomatal Density in Barley Improves Drought Tolerance without Impacting on Yield1[CC-BY] , 2017, Plant Physiology.

[10]  Joseph Howse,et al.  Learning OpenCV 3 computer vision with Python : unleash the power of computer vision with Python using OpenCV , 2015 .

[11]  Tam V. Nguyen,et al.  Ensemble of Deep Object Detectors for Page Object Detection , 2018, IMCOM.

[12]  Yann LeCun,et al.  Tangent Prop - A Formalism for Specifying Selected Invariances in an Adaptive Network , 1991, NIPS.

[13]  David Doermann,et al.  Handbook of Document Image Processing and Recognition , 2014, Springer London.

[14]  Davide Ballabio,et al.  Recent Advances in High-Level Fusion Methods to Classify Multiple Analytical Chemical Data , 2019, Data Handling in Science and Technology.

[15]  Yifan Yu,et al.  CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison , 2019, AAAI.

[16]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[17]  Jose George,et al.  Using YOLO based deep learning network for real time detection and localization of lung nodules from low dose CT scans , 2018, Medical Imaging.

[18]  J. Alison Noble,et al.  Omni-Supervised Learning: Scaling Up to Large Unlabelled Medical Datasets , 2018, MICCAI.

[19]  Patrice Y. Simard,et al.  Best practices for convolutional neural networks applied to visual document analysis , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[20]  Sergio Guadarrama,et al.  Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Kaiming He,et al.  Feature Pyramid Networks for Object Detection , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Nuno Vasconcelos,et al.  Cascade R-CNN: Delving Into High Quality Object Detection , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[23]  Luc Van Gool,et al.  The Pascal Visual Object Classes Challenge: A Retrospective , 2014, International Journal of Computer Vision.

[24]  Derek Anderson,et al.  Fusion of an Ensemble of Augmented Image Detectors for Robust Object Detection , 2018, Sensors.

[25]  Yuning Jiang,et al.  MegDet: A Large Mini-Batch Object Detector , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[26]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Jinhui Tang,et al.  CAD: Scale Invariant Framework for Real-Time Object Detection , 2017, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW).

[28]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Dan Boneh,et al.  Ensemble Adversarial Training: Attacks and Defenses , 2017, ICLR.

[30]  Zhoujun Li,et al.  TableBank: Table Benchmark for Image-based Table Detection and Recognition , 2019, LREC.

[31]  Adam Van Etten,et al.  You Only Look Twice: Rapid Multi-Scale Object Detection In Satellite Imagery , 2018, ArXiv.

[32]  Jian Guo,et al.  Deep CNN Ensemble with Data Augmentation for Object Detection , 2015, ArXiv.

[33]  Bulat Ibragimov,et al.  Deep neural network ensemble for pneumonia localization from a large-scale chest x-ray database , 2019, Comput. Electr. Eng..

[34]  J. D. Gaynor,et al.  Stomatal numbers of soybean and response to water stress , 1993, Plant and Soil.

[35]  Ali Farhadi,et al.  YOLOv3: An Incremental Improvement , 2018, ArXiv.

[36]  Larry S. Davis,et al.  Soft-NMS — Improving Object Detection with One Line of Code , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[37]  Xindong Wu,et al.  Object Detection With Deep Learning: A Review , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[38]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[39]  Zheng Zhang,et al.  MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems , 2015, ArXiv.

[40]  Seong-Il Yang,et al.  An Ensemble Method of CNN Models for Object Detection , 2018, 2018 International Conference on Information and Communication Technology Convergence (ICTC).

[41]  Toby P. Breckon,et al.  Using Deep Convolutional Neural Network Architectures for Object Classification and Detection Within X-Ray Baggage Security Imagery , 2018, IEEE Transactions on Information Forensics and Security.

[42]  Travis E. Oliphant,et al.  Guide to NumPy , 2015 .