Advertisement

Large Batch Optimization for Object Detection: Training COCO in 12 minutes

Conference paper
  • 736 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12366)

Abstract

Most of existing object detectors usually adopt a small training batch size (e.g. 16), which severely hinders the whole community from exploring large-scale datasets due to the extremely long training procedure. In this paper, we propose a versatile large batch optimization framework for object detection, named LargeDet, which successfully scales the batch size to larger than 1K for the first time. Specifically, we present a novel Periodical Moments Decay LAMB (PMD-LAMB) algorithm to effectively reduce the negative effects of the lagging historical gradients. Additionally, the Synchronized Batch Normalization (SyncBN) is utilized to help fast convergence. With LargeDet, we can not only prominently shorten the training period, but also significantly improve the detection accuracy of sparsely annotated large-scale datasets. For instance, we can finish the training of ResNet50 FPN detector on COCO within 12 min. Moreover, we achieve 12.2% mAP@0.5 absolute improvement for ResNet50 FPN on Open Images by training with batch size 640.

Keywords

Object detection Large batch optimization Periodical moments decay 

Notes

Acknowledgement

This work was supported by the Research and Development Projects in the Key Areas of Guangdong Province (No. 2019B010153001) and National Natural Science Foundation of China under Grants No. 61772527, No. 61976210, No. 61806200, No. 61702510, No. 61876086 and No. 61633002.

References

  1. 1.
    Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process. Mag. 29(6), 82–97 (2012).  https://doi.org/10.1109/MSP.2012.2205597
  2. 2.
    Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 5–10 December 2016, Barcelona, Spain, pp. 379–387 (2016). http://papers.nips.cc/paper/6465-r-fcn-object-detection-via-region-based-fully-convolutional-networks
  3. 3.
    Dai, J., et al.: Deformable convolutional networks. In: IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, 22–29 October 2017, pp. 764–773 (2017).  https://doi.org/10.1109/ICCV.2017.89
  4. 4.
    Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, 2–7 June 2019, Volume 1 (Long and Short Papers), pp. 4171–4186 (2019). https://www.aclweb.org/anthology/N19-1423/
  5. 5.
    Everingham, M., Gool, L.V., Williams, C.K.I., Winn, J.M., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303–338 (2010).  https://doi.org/10.1007/s11263-009-0275-4CrossRefGoogle Scholar
  6. 6.
    Goyal, P., et al.: Accurate, large minibatch SGD: training ImageNet in 1 hour. CoRR abs/1706.02677 (2017). http://arxiv.org/abs/1706.02677
  7. 7.
    He, K., Gkioxari, G., Dollár, P., Girshick, R.B.: Mask R-CNN. In: IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, 22–29 October 2017, pp. 2980–2988 (2017).  https://doi.org/10.1109/ICCV.2017.322
  8. 8.
    Keskar, N.S., Mudigere, D., Nocedal, J., Smelyanskiy, M., Tang, P.T.P.: On large-batch training for deep learning: generalization gap and sharp minima. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, 24–26 April 2017, Conference Track Proceedings (2017). https://openreview.net/forum?id=H1oyRlYgg
  9. 9.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7–9 May 2015, Conference Track Proceedings (2015). http://arxiv.org/abs/1412.6980
  10. 10.
    Krizhevsky, A.: One weird trick for parallelizing convolutional neural networks. CoRR abs/1404.5997 (2014). http://arxiv.org/abs/1404.5997
  11. 11.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a Meeting Held 3–6 December 2012, Lake Tahoe, Nevada, United States, pp. 1106–1114 (2012). http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks
  12. 12.
    Kuznetsova, A., et al.: The open images dataset V4: unified image classification, object detection, and visual relationship detection at scale. CoRR abs/1811.00982 (2018). http://arxiv.org/abs/1811.00982
  13. 13.
    Lin, T., Goyal, P., Girshick, R.B., He, K., Dollár, P.: Focal loss for dense object detection. In: IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, 22–29 October 2017, pp. 2999–3007 (2017).  https://doi.org/10.1109/ICCV.2017.324
  14. 14.
    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
  15. 15.
    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
  16. 16.
    Massa, F., Girshick, R.: maskRCNN-benchmark: fast, modular reference implementation of instance segmentation and object detection algorithms in PyTorch (2018). https://github.com/facebookresearch/maskrcnn-benchmark
  17. 17.
    Peng, C., et al.: MegDet: a large mini-batch object detector. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, 18–22 June 2018, pp. 6181–6189 (2018).  https://doi.org/10.1109/CVPR.2018.00647. http://openaccess.thecvf.com/content_cvpr_2018/html/Peng_MegDet_A_Large_CVPR_2018_paper.html
  18. 18.
    Redmon, J., Divvala, S.K., Girshick, R.B., Farhadi, A.: You only look once: unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, 27–30 June 2016, pp. 779–788 (2016).  https://doi.org/10.1109/CVPR.2016.91, https://doi.org/10.1109/CVPR.2016.91
  19. 19.
    Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137–1149 (2017).  https://doi.org/10.1109/TPAMI.2016.2577031CrossRefGoogle Scholar
  20. 20.
    Shao, S., Li, Z., Zhang, T., Peng, C., Yu, G., Zhang, X., Li, J., Sun, J.: Objects365: a large-scale, high-quality dataset for object detection. In: The IEEE International Conference on Computer Vision (ICCV), October 2019Google Scholar
  21. 21.
    Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 8–13 December 2014, Montreal, Quebec, Canada, pp. 3104–3112 (2014). http://papers.nips.cc/paper/5346-sequence-to-sequence-learning-with-neural-networks
  22. 22.
    Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: The IEEE International Conference on Computer Vision (ICCV), October 2019Google Scholar
  23. 23.
    You, Y., Gitman, I., Ginsburg, B.: Scaling SGD batch size to 32k for ImageNet training. CoRR abs/1708.03888 (2017). http://arxiv.org/abs/1708.03888
  24. 24.
    You, Y., Li, J., Hseu, J., Song, X., Demmel, J., Hsieh, C.: Reducing BERT pre-training time from 3 days to 76 minutes. CoRR abs/1904.00962 (2019). http://arxiv.org/abs/1904.00962
  25. 25.
    Zhou, X., Zhuo, J., Krahenbuhl, P.: Bottom-up object detection by grouping extreme and center points. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.National Laboratory of Pattern Recognition, Institute of AutomationChinese Academy of SciencesBeijingChina
  2. 2.School of Artificial IntelligenceUniversity of Chinese Academy of SciencesBeijingChina
  3. 3.ObjectEye Inc.BeijingChina
  4. 4.Peking UniversityBeijingChina
  5. 5.Peng Cheng LaboratoryShenzhenChina
  6. 6.NEXWISE Co., Ltd.GuangzhouChina

Personalised recommendations