Directly Optimizing IoU for Bounding Box Localization
Pages 544 - 556
Abstract
Object detection has seen remarkable progress in recent years with the introduction of Convolutional Neural Networks (CNN). Object detection is a multi-task learning problem where both the position of the objects in the images as well as their classes needs to be correctly identified. The idea here is to maximize the overlap between the ground-truth bounding boxes and the predictions i.e. the Intersection over Union (IoU). In the scope of work seen currently in this domain, IoU is approximated by using the Huber loss as a proxy but this indirect method does not leverage the IoU information and treats the bounding box as four independent, unrelated terms of regression. This is not true for a bounding box where the four coordinates are highly correlated and hold a semantic meaning when taken together. The direct optimization of the IoU is not possible due to its non-convex and non-differentiable nature. In this paper, we have formulated a novel loss namely, the Smooth IoU, which directly optimizes the IoUs for the bounding boxes. This loss has been evaluated on the Oxford IIIT Pets, Udacity self-driving car, PASCAL VOC, and VWFS Car Damage datasets and has shown performance gains over the standard Huber loss.
References
[1]
Box G and Hunter J Annals of mathematical statistics Ann. Math. Stat. 1956 27 4 1144-1151
[2]
Caruana RMultitask learningMach. Learn.199728141-752765508
[3]
Erhan, D., Szegedy, C., Toshev, A., Anguelov, D.: Scalable object detection using deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2147–2154 (2014)
[4]
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes challenge 2012 (VOC2012) results. http://www.pascal-network.org/challenges/VOC/voc2012/workshop/index.html
[5]
Girshick, R.: Fast R-CNN. In: The IEEE International Conference on Computer Vision (ICCV), December 2015
[6]
Huang, J., et al.: Speed/accuracy trade-offs for modern convolutional object detectors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7310–7311 (2017)
[7]
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)
[8]
Lin T-Y et al. Fleet D, Pajdla T, Schiele B, Tuytelaars T, et al. Microsoft COCO: common objects in context Computer Vision – ECCV 2014 2014 Cham Springer 740-755
[9]
Liu W et al. Leibe B, Matas J, Sebe N, Welling M, et al. SSD: single shot multibox detector Computer Vision – ECCV 2016 2016 Cham Springer 21-37
[10]
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
[11]
Nedic A and Bertsekas DPIncremental subgradient methods for nondifferentiable optimizationSIAM J. Optim.2001121109-1381870588
[12]
Nowozin, S.: Optimal decisions from probabilistic models: the intersection-over-union case. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 548–555 (2014)
[13]
Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.V.: Cats and dogs. In: IEEE Conference on Computer Vision and Pattern Recognition (2012)
[14]
Rahman MA, Wang Y, et al. Bebis G et al. Optimizing intersection-over-union in deep neural networks for image segmentation Advances in Visual Computing 2016 Cham Springer 234-244
[15]
Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263–7271 (2017)
[16]
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)
[17]
Rosasco L, Vito ED, Caponnetto A, Piana M, and Verri A Are loss functions all the same? Neural Comput. 2004 16 5 1063-1076
[18]
Russakovsky O et al.Imagenet large scale visual recognition challengeInt. J. Comput. Vis.20151153211-2523422482
[19]
Schaul, T., Zhang, S., LeCun, Y.: No more pesky learning rates. In: International Conference on Machine Learning, pp. 343–351 (2013)
[20]
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
[21]
Sutskever, I., Hinton, G.E., Krizhevsky, A.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
[22]
Szegedy, C., Reed, S., Erhan, D., Anguelov, D., Ioffe, S.: Scalable, high-quality object detection. arXiv preprint arXiv:1412.1441 (2014)
[23]
Tieleman, T., Hinton, G.: Rmsprop gradient optimization (2014). http://www.cs.toronto.edu/tijmen/csc321/slides/lecture_slides_lec6.pdf
[24]
Udacity: Self driving car (2017). https://github.com/udacity/self-driving-car/tree/master/annotations
[25]
Xu, Y., Lin, Q., Yang, T.: Stochastic convex optimization: faster local growth implies faster global convergence. In: Precup, D., Teh, Y.W. (eds.) Proceedings of the 34th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 70, pp. 3821–3830. PMLR, International Convention Centre, Sydney, Australia, 06–11 August 2017. http://proceedings.mlr.press/v70/xu17a.html
[26]
Yu, J., Jiang, Y., Wang, Z., Cao, Z., Huang, T.S.: UnitBox: an advanced object detection network. CoRR abs/1608.01471 (2016). http://arxiv.org/abs/1608.01471
Index Terms
- Directly Optimizing IoU for Bounding Box Localization
Index terms have been assigned to the content through auto-classification.
Recommendations
UnitBox: An Advanced Object Detection Network
MM '16: Proceedings of the 24th ACM international conference on MultimediaIn present object detection systems, the deep convolutional neural networks (CNNs) are utilized to predict bounding boxes of object candidates, and have gained performance advantages over the traditional region proposal methods. However, existing deep ...
Focal Iou loss: More attentive learning for bounding box regression
IoTML '24: Proceedings of the 2024 4th International Conference on Internet of Things and Machine LearningIn this paper, we investigate a more efficient IoU loss based bounding box localization mechanism on top of end-to-end target detection frameworks to further improve the regression accuracy of object detection methods. Aiming at the limited spatial ...
Hybrid dilated faster RCNN for object detection
Object detection is a very important part of computer vision, and the most common method of object detection is the Faster region convolutional neural network (RCNN), which uses CNN to extract image features. However, the parameters to be learned in CNN ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Nov 2019
942 pages
ISBN:978-3-030-41403-0
DOI:10.1007/978-3-030-41404-7
© Springer Nature Switzerland AG 2020.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 26 November 2019
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 18 Nov 2024
Other Metrics
Citations
View Options
View options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in