Instance Segmentation with Separable Convolutions and Multi-level Features

被引：0
|
作者：
Wang Z.-Y. [1 ]
Yuan C. [2 ]
Li J.-C. [2 ]
机构：
[1] Department of Computer Science and Technology, Tsinghua University, Beijing
[2] Graduate School at Shenzhen, Tsinghua University, Shenzhen
来源：
Ruan Jian Xue Bao/Journal of Software | 2019年 / 30卷 / 04期
关键词：
Boundary refinement; Instance segmentation; Multi-level feature; Separable convolution;
D O I：
10.13328/j.cnki.jos.005667
中图分类号：
学科分类号：
摘要：
Instance segmentation is a challenging task for it requires not only bounding-box of each instance but also precise segmentation mask of it. Recently proposed fully convolutional instance-aware semantic segmentation (FCIS) has done a good job in combining detection and segmentation. But FCIS cannot make use of low level features, which is proved useful in both detection and segmentation. Based on FCIS, a new model is proposed which refines the instance masks with features of all levels. In the proposed method, large kernel separable convolutions are employed in the detection branch to get more accurate bounding-boxes. Simultaneously, a segmentation module containing boundary refinement operation is designed to get more precise masks. Moreover, the low level, medium level, and high level features in Resnet-101 are combined into new features of four different levels, each of which is employed to generate a mask of an instance. These masks are added and refined to produce the final most accurate one. With the three improvements, the proposed approach significantly outperforms baseline FCIS as it provides 4.9% increase in mAPr@0.5 and 5.8% increase in mAPr @0.7 on PASCAL VOC. © Copyright 2019, Institute of Software, the Chinese Academy of Sciences. All rights reserved.
引用
收藏
页码：954 / 961
页数：7
相关论文
共 25 条
  • [1] Ren X.Q., He K.M., Girshick R., Sun J., Faster R-CNN: Towards real-time object detection with region proposal networks, Advances in Neural Information Processing Systems, pp. 91-99, (2015)
  • [2] Lin T.Y., Dollar P., Girshick R., He K.M., Hariharan B., Belongie S., Feature pyramid networks for object detection, Proc. of the Computer Vision and Pattern Recognition, pp. 1-4, (2017)
  • [3] Long J., Shelhamer E., Darrell T., Fully convolutional networks for semantic segmentation, Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, pp. 3431-3440, (2015)
  • [4] Chen L.C., Papandreou G., Schroff F., Adam H., Rethinking atrous convolution for semantic image segmentation, (2017)
  • [5] Yu F., Koltun V., Funkhouser T., Dilated residual networks, Proc. of the Computer Vision and Pattern Recognition, (2017)
  • [6] Lin G.S., Milan A., Shen C., Reid I., Refinenet: Multi-path refinement networks for high-resolution semantic segmentation, Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), (2017)
  • [7] Peng C., Zhang X.Y., Yu G., Luo G.M., Sun J., Large kernel matters-improve semantic segmentation by global convolutional network, (2017)
  • [8] Wang W., Shen J., Shao L., Et al., Correspondence driven saliency transfer, IEEE Trans. on Image Processing, 25, 11, pp. 5025-5034, (2016)
  • [9] Wang W., Shen J., Shao L., Video salient object detection via fully convolutional networks, IEEE Trans. on Image Processing, 27, 1, pp. 38-49, (2017)
  • [10] Pinheiro P.O., Collobert R., Dollar P., Learning to segment object candidates, Advances in Neural Information Processing Systems, pp. 1990-1998, (2015)
123