Advertisement

AABO: Adaptive Anchor Box Optimization for Object Detection via Bayesian Sub-sampling

Conference paper
  • 723 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12350)

Abstract

Most state-of-the-art object detection systems follow an anchor-based diagram. Anchor boxes are densely proposed over the images and the network is trained to predict the boxes position offset as well as the classification confidence. Existing systems pre-define anchor box shapes and sizes and ad-hoc heuristic adjustments are used to define the anchor configurations. However, this might be sub-optimal or even wrong when a new dataset or a new model is adopted. In this paper, we study the problem of automatically optimizing anchor boxes for object detection. We first demonstrate that the number of anchors, anchor scales and ratios are crucial factors for a reliable object detection system. By carefully analyzing the existing bounding box patterns on the feature hierarchy, we design a flexible and tight hyper-parameter space for anchor configurations. Then we propose a novel hyper-parameter optimization method named AABO to determine more appropriate anchor boxes for a certain dataset, in which Bayesian Optimization and sub-sampling method are combined to achieve precise and efficient anchor configuration optimization. Experiments demonstrate the effectiveness of our proposed method on different detectors and datasets, e.g. achieving around 2.4% mAP improvement on COCO, 1.6% on ADE and 1.5% on VG, and the optimal anchors can bring 1.4%–2.4% mAP improvement on SOTA detectors by only optimizing anchor configurations, e.g. boosting Mask RCNN from 40.3% to 42.3%, and HTC detector from 46.8% to 48.2%.

Keywords

Object detection Hyper-parameter optimization Bayesian optimization Sub-sampling 

Supplementary material

504441_1_En_33_MOESM1_ESM.pdf (5.2 mb)
Supplementary material 1 (pdf 5300 KB)

References

  1. 1.
    Bergstra, J.S., Bardenet, R., Bengio, Y., Kégl, B.: Algorithms for hyper-parameter optimization. In: NIPS (2011)Google Scholar
  2. 2.
    Bhagavatula, C., Zhu, C., Luu, K., Savvides, M.: Faster than real-time facial alignment: a 3D spatial transformer network approach in unconstrained poses. In: ICCV (2017)Google Scholar
  3. 3.
    Chabot, F., Chaouch, M., Rabarisoa, J., Teuliere, C., Chateau, T.: Deep manta: a coarse-to-fine many-task network for joint 2D and 3D vehicle analysis from monocular image. In: CVPR (2017)Google Scholar
  4. 4.
    Chan, H.P.: The multi-armed bandit problem: an efficient non-parametric solution. Ann. Stat. 48, 346–373 (2019)CrossRefGoogle Scholar
  5. 5.
    Chen, K., et al.: mmdetection (2018). https://github.com/open-mmlab/mmdetection
  6. 6.
    Chen, K., et al.: Hybrid task cascade for instance segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (2019)Google Scholar
  7. 7.
    Chen, X., Li, L.J., Fei-Fei, L., Gupta, A.: Iterative visual reasoning beyond convolutions. In: CVPR (2018)Google Scholar
  8. 8.
    Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: NIPS (2016)Google Scholar
  9. 9.
    Falkner, S., Klein, A., Hutter, F.: BOHB: robust and efficient hyperparameter optimization at scale. arXiv preprint arXiv:1807.01774 (2018)
  10. 10.
    He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: 2017 IEEE International Conference on Computer Vision (ICCV) (2017)Google Scholar
  11. 11.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)Google Scholar
  12. 12.
    Huang, Y., Li, Y., Li, Z., Zhang, Z.: An asymptotically optimal multi-armed bandit algorithm and hyperparameter optimization. arXiv e-prints arXiv:2007.05670 (2020)
  13. 13.
    Jamieson, K., Talwalkar, A.: Non-stochastic best arm identification and hyperparameter optimization. In: Artificial Intelligence and Statistics, pp. 240–248 (2016)Google Scholar
  14. 14.
    Jiang, C., Xu, H., Liang, X., Lin, L.: Hybrid knowledge routed modules for large-scale object detection. In: NIPS (2018)Google Scholar
  15. 15.
    Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123, 32–73 (2016)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Li, L., Jamieson, K., Desalvo, G., Rostamizadeh, A., Talwalkar, A.: Hyperband: a novel bandit-based approach to hyperparameter optimization. J. Mach. Learn. Res. 18, 1–52 (2016)MathSciNetzbMATHGoogle Scholar
  17. 17.
    Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR (2017)Google Scholar
  18. 18.
    Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: ICCV, pp. 2980–2988 (2017)Google Scholar
  19. 19.
    Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-10602-1_48CrossRefGoogle Scholar
  20. 20.
    Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46448-0_2CrossRefGoogle Scholar
  21. 21.
    Luo, P., Tian, Y., Wang, X., Tang, X.: Switchable deep network for pedestrian detection. In: CVPR (2014)Google Scholar
  22. 22.
    Mendoza, H., Klein, A., Feurer, M., Springenberg, J.T., Hutter, F.: Towards automatically-tuned neural networks. In: Workshop on Automatic Machine Learning, pp. 58–65 (2016)Google Scholar
  23. 23.
    Paszke, A., et al.: Automatic differentiation in pytorch. In: NIPS Workshop (2017)Google Scholar
  24. 24.
    Perchet, V., Rigollet, P.: The multi-armed bandit problem with covariates. Ann. Stat. 41(2), 693–721 (2013)MathSciNetCrossRefGoogle Scholar
  25. 25.
    Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR (2016)Google Scholar
  26. 26.
    Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: CVPR (2017)Google Scholar
  27. 27.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)Google Scholar
  28. 28.
    Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. IJCV 115(3), 211–252 (2015)MathSciNetCrossRefGoogle Scholar
  29. 29.
    Snoek, J., Larochelle, H., Adams, R.P.: Practical Bayesian optimization of machine learning algorithms. In: NIPS (2012)Google Scholar
  30. 30.
    Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)zbMATHGoogle Scholar
  31. 31.
    Tong, Y., Zhang, X., Zhang, W., Jian, S.: Metaanchor: learning to detect objects with customized anchors (2018)Google Scholar
  32. 32.
    Xie, S., Girshick, R., Dollár, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: CVPR, pp. 1492–1500 (2017)Google Scholar
  33. 33.
    Zhong, Y., Wang, J., Peng, J., Zhang, L.: Anchor box optimization for object detection. arXiv preprint arXiv:1812.00469 (2018)
  34. 34.
    Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: CVPR (2017)Google Scholar
  35. 35.
    Zhu, X., Hu, H., Lin, S., Dai, J.: Deformable convnets v2: more deformable, better results. arXiv preprint arXiv:1811.11168 (2018)

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Tsinghua UniversityBeijingChina
  2. 2.Huawei Noah’s Ark LabHong KongChina

Personalised recommendations