2020

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

Zhang, Hongkai, Chang, Hong, Ma, Bingpeng et al.

Understand

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.

Built on

Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: ICML (2009)
2009
Earlier work this paper cites.
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: A large-scale hierarchical image database. In: CVPR (2009)
2009
Earlier work this paper cites.
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. IJCV 88
2010
Earlier work this paper cites.
Kumar, M.P., Packer, B., Koller, D.: Self-paced learning for latent variable models. In: NIPS (2010)
2010
Earlier work this paper cites.
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS (2012)
2012
Earlier work this paper cites.
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)
2014
Earlier work this paper cites.
Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., Zitnick, C.L.: Microsoft COCO: Common objects in context. In: ECCV (2014)
2014
Earlier work this paper cites.
Girshick, R.: Fast R-CNN. In: ICCV (2015)
2015
Earlier work this paper cites.
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards real-time object detection with region proposal networks. In: NIPS (2015)
2015
Earlier work this paper cites.
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)
2015
Earlier work this paper cites.
Dai, J., Li, Y., He, K., Sun, J.: R-FCN: Object detection via region-based fully convolutional networks. In: NIPS (2016)
2016
Earlier work this paper cites.
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
2016
Earlier work this paper cites.
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., Berg, A.C.: SSD: Single shot multibox detector. In: ECCV (2016)
2016
Earlier work this paper cites.
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: CVPR (2016)
2016
Earlier work this paper cites.
Shrivastava, A., Gupta, A., Girshick, R.: Training region-based object detectors with online hard example mining. In: CVPR (2016)
2016
Earlier work this paper cites.
Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Soft-NMS – improving object detection with one line of code. In: ICCV (2017)
2017
Earlier work this paper cites.
Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., Wei, Y.: Deformable convolutional networks. In: ICCV (2017)
2017
Earlier work this paper cites.
He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)
2017
Earlier work this paper cites.

Similar

Huang, J., Rathod, V., Sun, C., Zhu, M., Korattikara, A., Fathi, A., Fischer, I., Wojna, Z., Song, Y., Guadarrama, S., Murphy, K.: Speed/accuracy trade-offs for modern convolutional object detectors. In: CVPR (2017)
2017
Cited alongside, same era.
Lin, T.Y., Dollar, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR (2017)
2017
Cited alongside, same era.
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollar, P.: Focal loss for dense object detection. In: ICCV (2017)
2017
Cited alongside, same era.
Loshchilov, I., Hutter, F.: SGDR: Stochastic gradient descent with warm restarts. In: ICLR (2017)
2017
Cited alongside, same era.
Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., Lerer, A.: Automatic differentiation in PyTorch. In: NIPS Workshop (2017)
2017
Cited alongside, same era.
Cai, Z., Vasconcelos, N.: Cascade R-CNN: Delving into high quality object detection. In: CVPR (2018)
2018
Cited alongside, same era.
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)
2018
Cited alongside, same era.
Girshick, R., Radosavovic, I., Gkioxari, G., Dollár, P., He, K.: Detectron. https://github.com/facebookresearch/detectron (2018)
2018
Cited alongside, same era.
Jiang, B., Luo, R., Mao, J., Xiao, T., Jiang, Y.: Acquisition of localization confidence for accurate object detection. In: ECCV (2018)
2018
Cited alongside, same era.
Kendall, A., Gal, Y., Cipolla, R.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: CVPR (2018)
2018
Cited alongside, same era.
Law, H., Deng, J.: CornerNet: Detecting objects as paired keypoints. In: ECCV (2018)
2018
Cited alongside, same era.
Li, Z., Peng, C., Yu, G., Zhang, X., Deng, Y., Sun, J.: DetNet: Design backbone for object detection. In: ECCV (2018)
2018
Cited alongside, same era.

Then

Chen, Y., Han, C., Wang, N., Zhang, Z.: Revisiting feature alignment for one-stage object detection. arXiv:1908.01570 (2019)
Original
2019
Later among the works it cites.
He, Y., Zhu, C., Wang, J., Savvides, M., Zhang, X.: Bounding box regression with uncertainty for accurate object detection. In: CVPR (2019)
2019
Later among the works it cites.
Li, Y., Chen, Y., Wang, N., Zhang, Z.: Scale-aware trident networks for object detection. In: ICCV (2019)
2019
Later among the works it cites.
Pang, J., Chen, K., Shi, J., Feng, H., Ouyang, W., Lin, D.: Libra R-CNN: Towards balanced learning for object detection. In: CVPR (2019)
2019
Later among the works it cites.
Tan, Z., Nie, X., Qian, Q., Li, N., Li, H.: Learning to rank proposals for object detection. In: ICCV (2019)
2019
Later among the works it cites.
Tian, Z., Shen, C., Chen, H., He, T.: FCOS: Fully convolutional one-stage object detection. In: ICCV (2019)
2019
Later among the works it cites.
Wang, J., Chen, K., Yang, S., Loy, C.C., Lin, D.: Region proposal by guided anchoring. In: CVPR (2019)
2019
Later among the works it cites.
Yang, Z., Liu, S., Hu, H., Wang, L., Lin, S.: RepPoints: Point set representation for object detection. In: ICCV (2019)
2019
Later among the works it cites.
Zhang, H., Chang, H., Ma, B., Shan, S., Chen, X.: Cascade RetinaNet: Maintaining consistency for single-stage object detection. In: BMVC (2019)
2019
Later among the works it cites.
Zhang, X., Wan, F., Liu, C., Ji, R., Ye, Q.: FreeAnchor: Learning to match anchors for visual object detection. In: NeurIPS (2019)
2019
Later among the works it cites.
Zhou, X., Wang, D., Krähenbühl, P.: Objects as points. arXiv:1904.07850 (2019)
Original
2019
Later among the works it cites.
Zhu, X., Hu, H., Lin, S., Dai, J.: Deformable convnets v2: More deformable, better results. In: CVPR (2019)
2019
Later among the works it cites.
Gu, X., Chang, H., Ma, B., Zhang, H., Chen, X.: Appearance-preserving 3d convolution for video-based person re-identification. In: ECCV (2020)
2020
Closest in time.
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)
2020
Closest in time.
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)
2020
Closest in time.
Wang, J., Zhang, W., Cao, Y., Chen, K., Pang, J., Gong, T., Shi, J., Loy, C.C., Lin, D.: Side-aware boundary localization for more precise object detection. In: ECCV (2020)
2020
Closest in time.
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)
2020
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…