Advertisement

Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12360)

Abstract

Although two-stage object detectors have continuously advanced the state-of-the-art performance in recent years, the training process itself is far from crystal. In this work, we first point out the inconsistency problem between the fixed network settings and the dynamic training procedure, which greatly affects the performance. For example, the fixed label assignment strategy and regression loss function cannot fit the distribution change of proposals and thus are harmful to training high quality detectors. Consequently, we propose Dynamic R-CNN to adjust the label assignment criteria (IoU threshold) and the shape of regression loss function (parameters of SmoothL1 Loss) automatically based on the statistics of proposals during training. This dynamic design makes better use of the training samples and pushes the detector to fit more high quality samples. Specifically, our method improves upon ResNet-50-FPN baseline with 1.9% AP and 5.5% AP\(_{90}\) on the MS COCO dataset with no extra overhead. Codes and models are available at https://github.com/hkzhang95/DynamicRCNN.

Keywords

Dynamic training High quality object detection 

Notes

Acknowledgements

This work is partially supported by Natural Science Foundation of China (NSFC): 61876171 and 61976203, and Beijing Natural Science Foundation under Grant L182054.

Supplementary material

504470_1_En_16_MOESM1_ESM.pdf (121 kb)
Supplementary material 1 (pdf 120 KB)

References

  1. 1.
    Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: ICML (2009)Google Scholar
  2. 2.
    Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Soft-NMS - improving object detection with one line of code. In: ICCV (2017)Google Scholar
  3. 3.
    Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: CVPR (2018)Google Scholar
  4. 4.
    Chen, Y., et al.: SimpleDet: a simple and versatile distributed framework for object detection and instance recognition. JMLR 20(156), 1–8 (2019)Google Scholar
  5. 5.
    Chen, Y., Han, C., Wang, N., Zhang, Z.: Revisiting feature alignment for one-stage object detection. arXiv:1908.01570 (2019)
  6. 6.
    Cheng, B., Wei, Y., Shi, H., Feris, R., Xiong, J., Huang, T.: Revisiting RCNN: on awakening the classification power of faster RCNN. In: ECCV (2018)Google Scholar
  7. 7.
    Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: NIPS (2016)Google Scholar
  8. 8.
    Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., Wei, Y.: Deformable convolutional networks. In: ICCV (2017)Google Scholar
  9. 9.
    Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)Google Scholar
  10. 10.
    Girshick, R.: Fast R-CNN. In: ICCV (2015)Google Scholar
  11. 11.
    Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)Google Scholar
  12. 12.
    Girshick, R., Radosavovic, I., Gkioxari, G., Dollár, P., He, K.: Detectron (2018). https://github.com/facebookresearch/detectron
  13. 13.
    Gu, X., Chang, H., Ma, B., Zhang, H., Chen, X.: Appearance-preserving 3D convolution for video-based person re-identification. In: ECCV (2020)Google Scholar
  14. 14.
    He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)Google Scholar
  15. 15.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)Google Scholar
  16. 16.
    He, Y., Zhu, C., Wang, J., Savvides, M., Zhang, X.: Bounding box regression with uncertainty for accurate object detection. In: CVPR (2019)Google Scholar
  17. 17.
    Huang, J., et al.: Speed/accuracy trade-offs for modern convolutional object detectors. In: CVPR (2017)Google Scholar
  18. 18.
    Jiang, B., Luo, R., Mao, J., Xiao, T., Jiang, Y.: Acquisition of localization confidence for accurate object detection. In: ECCV (2018)Google Scholar
  19. 19.
    Jiang, Z., Liu, Y., Yang, C., Liu, J., Gao, P., Zhang, Q., Xiang, S., Pan, C.: Learning where to focus for efficient video object detection. In: ECCV (2020).  https://doi.org/10.1007/978-3-030-58517-4_2
  20. 20.
    Kendall, A., Gal, Y., Cipolla, R.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: CVPR (2018)Google Scholar
  21. 21.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS (2012)Google Scholar
  22. 22.
    Kumar, M.P., Packer, B., Koller, D.: Self-paced learning for latent variable models. In: NIPS (2010)Google Scholar
  23. 23.
    Law, H., Deng, J.: CornerNet: detecting objects as paired keypoints. In: ECCV (2018)Google Scholar
  24. 24.
    Li, H., Wu, Z., Zhu, C., Xiong, C., Socher, R., Davis, L.S.: Learning from noisy anchors for one-stage object detection. In: CVPR (2020)Google Scholar
  25. 25.
    Li, Y., Chen, Y., Wang, N., Zhang, Z.: Scale-aware trident networks for object detection. In: ICCV (2019)Google Scholar
  26. 26.
    Li, Z., Peng, C., Yu, G., Zhang, X., Deng, Y., Sun, J.: DetNet: design backbone for object detection. In: ECCV (2018)Google Scholar
  27. 27.
    Lin, T.Y., Dollar, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR (2017)Google Scholar
  28. 28.
    Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollar, P.: Focal loss for dense object detection. In: ICCV (2017)Google Scholar
  29. 29.
    Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: ECCV (2014)Google Scholar
  30. 30.
    Liu, S., Huang, D., Wang, Y.: Receptive field block net for accurate and fast object detection. In: ECCV (2018)Google Scholar
  31. 31.
    Liu, W., et al.: SSD: Single shot multibox detector. In: ECCV (2016)Google Scholar
  32. 32.
    Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. In: ICLR (2017)Google Scholar
  33. 33.
    Pang, J., Chen, K., Shi, J., Feng, H., Ouyang, W., Lin, D.: Libra R-CNN: towards balanced learning for object detection. In: CVPR (2019)Google Scholar
  34. 34.
    Paszke, A., et al.: Automatic differentiation in PyTorch. In: NIPS Workshop (2017)Google Scholar
  35. 35.
    Peng, C., et al.: MegDet: a large mini-batch object detector. In: CVPR (2018)Google Scholar
  36. 36.
    Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR (2016)Google Scholar
  37. 37.
    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
  38. 38.
    Shrivastava, A., Gupta, A., Girshick, R.: Training region-based object detectors with online hard example mining. In: CVPR (2016)Google Scholar
  39. 39.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)Google Scholar
  40. 40.
    Singh, B., Davis, L.S.: An analysis of scale invariance in object detection - SNIP. In: CVPR (2018)Google Scholar
  41. 41.
    Tan, Z., Nie, X., Qian, Q., Li, N., Li, H.: Learning to rank proposals for object detection. In: ICCV (2019)Google Scholar
  42. 42.
    Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: ICCV (2019)Google Scholar
  43. 43.
    Wang, J., Chen, K., Yang, S., Loy, C.C., Lin, D.: Region proposal by guided anchoring. In: CVPR (2019)Google Scholar
  44. 44.
    Wang, J., et al.: Side-aware boundary localization for more precise object detection. In: ECCV (2020)Google Scholar
  45. 45.
    Xu, H., Lv, X., Wang, X., Ren, Z., Bodla, N., Chellappa, R.: Deep regionlets for object detection. In: ECCV (2018)Google Scholar
  46. 46.
    Yang, Z., Liu, S., Hu, H., Wang, L., Lin, S.: RepPoints: point set representation for object detection. In: ICCV (2019)Google Scholar
  47. 47.
    Zhang, H., Chang, H., Ma, B., Shan, S., Chen, X.: Cascade RetinaNet: maintaining consistency for single-stage object detection. In: BMVC (2019)Google Scholar
  48. 48.
    Zhang, S., Chi, C., Yao, Y., Lei, Z., Li, S.Z.: Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: CVPR (2020)Google Scholar
  49. 49.
    Zhang, X., Wan, F., Liu, C., Ji, R., Ye, Q.: FreeAnchor: learning to match anchors for visual object detection. In: NeurIPS (2019)Google Scholar
  50. 50.
    Zhou, X., Wang, D., Krähenbühl, P.: Objects as points. arXiv:1904.07850 (2019)
  51. 51.
    Zhu, X., Hu, H., Lin, S., Dai, J.: Deformable convnets v2: more deformable, better results. In: CVPR (2019)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS)Institute of Computing Technology, Chinese Academy of SciencesBeijingChina
  2. 2.University of Chinese Academy of SciencesBeijingChina
  3. 3.TuSimpleSan DiegoUSA

Personalised recommendations