Abstract
We present a reinforcement learning approach for detecting objects within an image. Our approach performs a step-wise deformation of a bounding box with the goal of tightly framing the object. It uses a hierarchical tree-like representation of predefined region candidates, which the agent can zoom in on. This reduces the number of region candidates that must be evaluated so that the agent can afford to compute new feature maps before each step to enhance detection quality. We compare an approach that is based purely on zoom actions with one that is extended by a second refinement stage to fine-tune the bounding box after each zoom step. We also improve the fitting ability by allowing for different aspect ratios of the bounding box. Finally, we propose different reward functions to lead to a better guidance of the agent while following its search trajectories. Experiments indicate that each of these extensions leads to more correct detections. The best performing approach comprises a zoom stage and a refinement stage, uses aspect-ratio modifying actions and is trained using a combination of three different reward metrics.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Itti, L., Rees, G., Tsotsos, J.K.: Neurobiology of attention (2005)
Mathe, S., Pirinen, A., Sminchisescu, C.: Reinforcement learning for visual object detection. IEEE (2016)
Bueno, M.B., Nieto, X.G., Marqués, F., Torres, J.: Hierarchical object detection with deep reinforcement learning. arXiv:1611.03718v2 (2016)
Uijlings, J.R., Van De Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. Int. J. Comput. Vis. 104, 154–171 (2013)
Zitnick, C.L., Piotr, D.: Edge boxes: locating object proposals from edges. In: European Conference on Computer Vision (2014)
Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)
Caicedo, J.C., Lazebnik, S.: Active object localization with deep reinforcement learning. IEEE (2015)
Maicas, G., Carneiro, G., Bradley, A.P., Nascimento, J.C., Reid, I.: Deep reinforcement learning for active breast lesion detection from DCE-MRI. In: 2007 International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham (2017)
Watkins, C.J.C.H.: Learning from Delayed Rewards (1989)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556v6 (2015)
Mataric, M.J.: Reward functions for accelerated learning. Mach. Learn. Proc. 1994, 181–189 (1994)
Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML-2010), pp. 807–814 (2010)
Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. In: Journal of Machine Learning Research, pp. 1929–1958, 2014
Kingma, D., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The Pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 303–338 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendices
A Algorithm
B Evaluation Overview
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
König, J., Malberg, S., Martens, M., Niehaus, S., Krohn-Grimberghe, A., Ramaswamy, A. (2020). Multi-stage Reinforcement Learning for Object Detection. In: Arai, K., Kapoor, S. (eds) Advances in Computer Vision. CVC 2019. Advances in Intelligent Systems and Computing, vol 943. Springer, Cham. https://doi.org/10.1007/978-3-030-17795-9_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-17795-9_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-17794-2
Online ISBN: 978-3-030-17795-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)