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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Specifically, high quality represents the results under high IoU.
- 2.
References
Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: ICML (2009)
Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Soft-NMS - improving object detection with one line of code. In: ICCV (2017)
Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: CVPR (2018)
Chen, Y., et al.: SimpleDet: a simple and versatile distributed framework for object detection and instance recognition. JMLR 20(156), 1–8 (2019)
Chen, Y., Han, C., Wang, N., Zhang, Z.: Revisiting feature alignment for one-stage object detection. arXiv:1908.01570 (2019)
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)
Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: NIPS (2016)
Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., Wei, Y.: Deformable convolutional networks. In: ICCV (2017)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)
Girshick, R.: Fast R-CNN. In: ICCV (2015)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)
Girshick, R., Radosavovic, I., Gkioxari, G., Dollár, P., He, K.: Detectron (2018). https://github.com/facebookresearch/detectron
Gu, X., Chang, H., Ma, B., Zhang, H., Chen, X.: Appearance-preserving 3D convolution for video-based person re-identification. In: ECCV (2020)
He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
He, Y., Zhu, C., Wang, J., Savvides, M., Zhang, X.: Bounding box regression with uncertainty for accurate object detection. In: CVPR (2019)
Huang, J., et al.: Speed/accuracy trade-offs for modern convolutional object detectors. In: CVPR (2017)
Jiang, B., Luo, R., Mao, J., Xiao, T., Jiang, Y.: Acquisition of localization confidence for accurate object detection. In: ECCV (2018)
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
Kendall, A., Gal, Y., Cipolla, R.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: CVPR (2018)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS (2012)
Kumar, M.P., Packer, B., Koller, D.: Self-paced learning for latent variable models. In: NIPS (2010)
Law, H., Deng, J.: CornerNet: detecting objects as paired keypoints. In: ECCV (2018)
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)
Li, Y., Chen, Y., Wang, N., Zhang, Z.: Scale-aware trident networks for object detection. In: ICCV (2019)
Li, Z., Peng, C., Yu, G., Zhang, X., Deng, Y., Sun, J.: DetNet: design backbone for object detection. In: ECCV (2018)
Lin, T.Y., Dollar, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR (2017)
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollar, P.: Focal loss for dense object detection. In: ICCV (2017)
Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: ECCV (2014)
Liu, S., Huang, D., Wang, Y.: Receptive field block net for accurate and fast object detection. In: ECCV (2018)
Liu, W., et al.: SSD: Single shot multibox detector. In: ECCV (2016)
Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. In: ICLR (2017)
Pang, J., Chen, K., Shi, J., Feng, H., Ouyang, W., Lin, D.: Libra R-CNN: towards balanced learning for object detection. In: CVPR (2019)
Paszke, A., et al.: Automatic differentiation in PyTorch. In: NIPS Workshop (2017)
Peng, C., et al.: MegDet: a large mini-batch object detector. In: CVPR (2018)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR (2016)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)
Shrivastava, A., Gupta, A., Girshick, R.: Training region-based object detectors with online hard example mining. In: CVPR (2016)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)
Singh, B., Davis, L.S.: An analysis of scale invariance in object detection - SNIP. In: CVPR (2018)
Tan, Z., Nie, X., Qian, Q., Li, N., Li, H.: Learning to rank proposals for object detection. In: ICCV (2019)
Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: ICCV (2019)
Wang, J., Chen, K., Yang, S., Loy, C.C., Lin, D.: Region proposal by guided anchoring. In: CVPR (2019)
Wang, J., et al.: Side-aware boundary localization for more precise object detection. In: ECCV (2020)
Xu, H., Lv, X., Wang, X., Ren, Z., Bodla, N., Chellappa, R.: Deep regionlets for object detection. In: ECCV (2018)
Yang, Z., Liu, S., Hu, H., Wang, L., Lin, S.: RepPoints: point set representation for object detection. In: ICCV (2019)
Zhang, H., Chang, H., Ma, B., Shan, S., Chen, X.: Cascade RetinaNet: maintaining consistency for single-stage object detection. In: BMVC (2019)
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)
Zhang, X., Wan, F., Liu, C., Ji, R., Ye, Q.: FreeAnchor: learning to match anchors for visual object detection. In: NeurIPS (2019)
Zhou, X., Wang, D., Krähenbühl, P.: Objects as points. arXiv:1904.07850 (2019)
Zhu, X., Hu, H., Lin, S., Dai, J.: Deformable convnets v2: more deformable, better results. In: CVPR (2019)
Acknowledgements
This work is partially supported by Natural Science Foundation of China (NSFC): 61876171 and 61976203, and Beijing Natural Science Foundation under Grant L182054.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, H., Chang, H., Ma, B., Wang, N., Chen, X. (2020). Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12360. Springer, Cham. https://doi.org/10.1007/978-3-030-58555-6_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-58555-6_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58554-9
Online ISBN: 978-3-030-58555-6
eBook Packages: Computer ScienceComputer Science (R0)