Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression

Intersection over Union (IoU) is the most popular evaluation metric used in the object detection benchmarks. However, there is a gap between optimizing the commonly used distance losses for regressing the parameters of a bounding box and maximizing this metric value. The optimal objective for a metric is the metric itself. In the case of axis-aligned 2D bounding boxes, it can be shown that IoU can be directly used as a regression loss. However, IoU has a plateau making it infeasible to optimize in the case of non-overlapping bounding boxes. In this paper, we address the this weakness by introducing a generalized version of IoU as both a new loss and a new metric. By incorporating this generalized IoU ( GIoU) as a loss into the state-of-the art object detection frameworks, we show a consistent improvement on their performance using both the standard, IoU based, and new, GIoU based, performance measures on popular object detection benchmarks such as PASCAL VOC and MS COCO.

[1]  Sven Kosub,et al.  A note on the triangle inequality for the Jaccard distance , 2016, Pattern Recognit. Lett..

[2]  Yuning Jiang,et al.  UnitBox: An Advanced Object Detection Network , 2016, ACM Multimedia.

[3]  Koen E. A. van de Sande,et al.  Selective Search for Object Recognition , 2013, International Journal of Computer Vision.

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

[5]  Yang Wang,et al.  Optimizing Intersection-Over-Union in Deep Neural Networks for Image Segmentation , 2016, ISVC.

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

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

[8]  M. Levandowsky,et al.  Distance between Sets , 1971, Nature.

[9]  Zhenyu He,et al.  The Visual Object Tracking VOT2016 Challenge Results , 2016, ECCV Workshops.

[10]  Sebastian Ramos,et al.  The Cityscapes Dataset for Semantic Urban Scene Understanding , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[12]  Matthew B. Blaschko,et al.  The Lovasz-Softmax Loss: A Tractable Surrogate for the Optimization of the Intersection-Over-Union Measure in Neural Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[13]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[14]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

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

[16]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[18]  A. H. Lipkus.  A proof of the triangle inequality for the Tanimoto distance , 1999 .

[19]  Ross B. Girshick,et al.  Focal Loss for Dense Object Detection , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Yuning Jiang,et al.  Acquisition of Localization Confidence for Accurate Object Detection , 2018, ECCV.

[21]  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.

[22]  Shu Liu,et al.  Path Aggregation Network for Instance Segmentation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[23]  Andreas Geiger,et al.  Augmented Reality Meets Computer Vision: Efficient Data Generation for Urban Driving Scenes , 2017, International Journal of Computer Vision.

[24]  Bolei Zhou,et al.  Scene Parsing through ADE20K Dataset , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[26]  Yi Li,et al.  R-FCN: Object Detection via Region-based Fully Convolutional Networks , 2016, NIPS.