Advertisement

CDSSD: Refreshing Single Shot Object Detection Using a Conv-Deconv Network

  • Vijay Gabale
  • Uma Sawant
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10939)

Abstract

Single shot multi-box object detectors [13] have been recently shown to achieve state-of-the-art performance on object detection tasks. We extend the single shot detection (SSD) framework in [13] and propose a generic architecture using a deep convolution-deconvolution network. Our architecture does not rely on any pretrained network, and can be pretrained in an unsupervised manner for a given image dataset. Furthermore, we propose a novel approach to combine feature maps from both convolution and deconvolution layers to predict bounding boxes and labels with improved accuracy. Our framework, Conv-Deconv SSD (CDSSD), with its two key contributions – unsupervised pretraining and multi-layer confluence of convolution-deconvolution feature maps – results in state-of-the-art performance while utilizing significantly less number of bounding boxes and improved identification of small objects. On \(300 \times 300\) image inputs, we achieve 80.7% mAP on VOC07 and 78.1% mAP on VOC07+12 (1.7% to 2.8% improvement over StairNet [21], DSSD [5], SSD [13]). CDSSD achieves 30.2% mAP on COCO performing at-par with R-FCN [3] and faster-R-FCN [18], while working on smaller size input images. Furthermore, CDSSD matches SSD performance while utilizing 82% of data, and reduces the prediction time per image by 10%.

Keywords

Single shot detection Unsupervised learning Feature map confluence 

References

  1. 1.
    Bell, S., Zitnick, C.L., Bala, K., Girshick, R.: Inside-outside net: detecting objects in context with skip pooling and recurrent neural networks. In: CVPR (2016)Google Scholar
  2. 2.
    Cai, Z., Fan, Q., Feris, R.S., Vasconcelos, N.: A unified multi-scale deep convolutional neural network for fast object detection. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 354–370. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46493-0_22CrossRefGoogle Scholar
  3. 3.
    Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. CoRR abs/1605.06409 (2016)Google Scholar
  4. 4.
    Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. IJCV 88(2), 303–338 (2010)CrossRefGoogle Scholar
  5. 5.
    Fu, C., Liu, W., Ranga, A., Tyagi, A., Berg, A.C.: DSSD: deconvolutional single shot detector. CoRR abs/1701.06659 (2017)Google Scholar
  6. 6.
    Girshick, R.: Fast R-CNN. In: ICCV (2015)Google Scholar
  7. 7.
    Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)Google Scholar
  8. 8.
    He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. CoRR abs/1406.4729 (2014)Google Scholar
  9. 9.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR abs/1512.03385 (2015)Google Scholar
  10. 10.
    Jeong, J., Park, H., Kwak, N.: Enhancement of SSD by concatenating feature maps for object detection. CoRR abs/1705.09587 (2017)Google Scholar
  11. 11.
    Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR (2017)Google Scholar
  12. 12.
    Lin, T., Maire, M., Belongie, S.J., Bourdev, L.D., Girshick, R.B., Hays, J., Perona, P., Ramanan, D., Dollár, P., Zitnick, C.L.: Microsoft COCO: common objects in context. CoRR abs/1405.0312 (2014)Google Scholar
  13. 13.
    Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: 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
  14. 14.
    Luo, W., Li, Y., Urtasun, R., Zemel, R.S.: Understanding the effective receptive field in deep convolutional neural networks. CoRR abs/1701.04128 (2017)Google Scholar
  15. 15.
    Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. CoRR abs/1505.04366 (2015)Google Scholar
  16. 16.
    Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: CVPR (2016)Google Scholar
  17. 17.
    Ren, J.S.J., Chen, X., Liu, J., Sun, W., Pang, J., Yan, Q., Tai, Y.W., Xu, L.: Accurate single stage detector using recurrent rolling convolution. In: CVPR (2017)Google Scholar
  18. 18.
    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
  19. 19.
    Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., Lecun, Y.: OverFeat: integrated recognition, localization and detection using convolutional networks. In: ICLR (2014)Google Scholar
  20. 20.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556 (2014)Google Scholar
  21. 21.
    Woo, S., Hwang, S., Kweon, I.S.: StairNet: top-down semantic aggregation for accurate one shot detection. CoRR abs/1709.05788 (2017)Google Scholar
  22. 22.
    Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. CoRR abs/1511.07122 (2015)Google Scholar
  23. 23.
    Zhou, B., Khosla, A., Lapedriza, À., Oliva, A., Torralba, A.: Object detectors emerge in deep scene CNNs. CoRR abs/1412.6856 (2014)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.HuewBangaloreIndia
  2. 2.IIT BombayMumbaiIndia

Personalised recommendations