Abstract
Recent one-stage CNN based detectors attract lots of research interests due to the high detection efficiency. However, their detection accuracy usually is not good enough. The major reason is that with only one regression step, one-stage detectors like SSD build features which are not representative enough for both classification and localization. In this paper, we propose a novel module, Comprehensive Feature Enhancement (CFE) module, for largely enhancing the features of one-stage detectors. The effective yet lightweight module could improve the detection accuracy with only increasing little inference time. Moreover, we propose two new one-stage detectors by assembling CFEs into the original SSD: CFE-SSDv1 and CFE-SSDv2. The CFE-SSDv1 is of simple structure with high efficiency while CFE-SSDv2 is more accurate and improves dramatically on detecting small objects especially. We evaluate the proposed CFE-SSDv1 and CFE-SSDv2 on two benchmarks for general object detection: PASCAL VOC07 and MS COCO. Experimental results show that CFE-SSDv2 outperforms state-of-the-art one-stage methods such as DSSD and RefineDet on these two benchmarks. Moreover, additional ablation study demonstrates the effectiveness of the proposed CFE module. We further test the proposed CFE-SSDv2 on UA-DETRAC dataset for vehicle detection and BDD dataset for road object detection, and both get accurate detection results compared with other state-of-the-art methods.
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
References
Bell, S., Zitnick, C.L., Bala, K., Girshick, R.B.: Inside-outside net: detecting objects in context with skip pooling and recurrent neural networks. In: CVPR 2016, pp. 2874–2883 (2016)
Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: CVPR 2017, pp. 1800–1807 (2017)
Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: NIPS (2016)
Everingham, M., Gool, L.J.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)
Fu, C., Liu, W., Ranga, A., Tyagi, A., Berg, A.C.: DSSD: deconvolutional single shot detector. CoRR abs/1701.06659 (2017)
Gidaris, S., Komodakis, N.: Object detection via a multi-region and semantic segmentation-aware CNN model. In: ICCV 2015, pp. 1134–1142 (2015)
Girshick, R.B.: Fast R-CNN. In: ICCV 2015, pp. 1440–1448 (2015)
Girshick, R.B., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR 2014, pp. 580–587 (2014)
He, K., Gkioxari, G., Dollár, P., Girshick, R.B.: Mask R-CNN. In: ICCV (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: ICCV 2015, pp. 1026–1034 (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR 2016, pp. 770–778 (2016)
Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. CoRR abs/1704.04861 (2017)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: CVPR (2018)
Kong, T., Sun, F., Yao, A., Liu, H., Lu, M., Chen, Y.: RON: reverse connection with objectness prior networks for object detection. In: CVPR 2017, pp. 5244–5252 (2017)
Kong, T., Yao, A., Chen, Y., Sun, F.: HyperNet: towards accurate region proposal generation and joint object detection. In: CVPR 2016, pp. 845–853 (2016)
Li, Z., Peng, C., Yu, G., Zhang, X., Deng, Y., Sun, J.: Light-head R-CNN: in defense of two-stage object detector. CoRR abs/1711.07264 (2017)
Lin, M., Chen, Q., Yan, S.: Network in network. In: ICLR (2014)
Lin, T., Dollár, P., Girshick, R.B., He, K., Hariharan, B., Belongie, S.J.: Feature pyramid networks for object detection. In: CVPR 2017, pp. 936–944 (2017)
Lin, T., Goyal, P., Girshick, R.B., He, K., Dollár, P.: Focal loss for dense object detection. In: ICCV 2017, pp. 2999–3007 (2017)
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_48
Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: CVPR (2018)
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_2
Peng, C., Zhang, X., Yu, G., Luo, G., Sun, J.: Large kernel matters - improve semantic segmentation by global convolutional network. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21–26 July 2017, pp. 1743–1751 (2017)
Redmon, J., Divvala, S.K., Girshick, R.B., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR 2016, pp. 779–788 (2016)
Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: CVPR 2017, pp. 6517–6525 (2017)
Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv (2018)
Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Annual Conference on Neural Information Processing Systems 2015, pp. 91–99 (2015)
Shen, Z., Liu, Z., Li, J., Jiang, Y., Chen, Y., Xue, X.: DSOD: learning deeply supervised object detectors from scratch. In: ICCV 2017, pp. 1937–1945 (2017)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556 (2014)
Szegedy, C., et al.: Going deeper with convolutions. In: CVPR 2015, pp. 1–9 (2015)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR 2016, pp. 2818–2826 (2016)
Uijlings, J.R.R., van de Sande, K.E.A., Gevers, T., Smeulders, A.W.M.: Selective search for object recognition. Int. J. Comput. Vis 104(2), 154–171 (2013)
Wen, L., et al.: UA-DETRAC: a new benchmark and protocol for multi-object detection and tracking. arXiv CoRR abs/1511.04136 (2015)
Xie, S., Girshick, R.B., Dollár, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: CVPR 2017, pp. 5987–5995 (2017)
Yu, F., et al.: BDD100K: a diverse driving video database with scalable annotation tooling. CoRR abs/1805.04687 (2018)
Zhang, S., Wen, L., Bian, X., Lei, Z., Li, S.Z.: Single-shot refinement neural network for object detection. In: CVPR (2018)
Acknowledgement
This work is supported by National Natural Science Foundation of China under Grant 61673029. This work is also a research achievement of Key Laboratory of Science, Technology and Standard in Press Industry (Key Laboratory of Intelligent Press Media Technology).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhao, Q., Wang, Y., Sheng, T., Tang, Z. (2019). Comprehensive Feature Enhancement Module for Single-Shot Object Detector. In: Jawahar, C., Li, H., Mori, G., Schindler, K. (eds) Computer Vision – ACCV 2018. ACCV 2018. Lecture Notes in Computer Science(), vol 11365. Springer, Cham. https://doi.org/10.1007/978-3-030-20873-8_21
Download citation
DOI: https://doi.org/10.1007/978-3-030-20873-8_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-20872-1
Online ISBN: 978-3-030-20873-8
eBook Packages: Computer ScienceComputer Science (R0)