Skip to main content
Article
SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation.
arXiv: Computer Vision and Pattern Recognition
  • Jiale Cao
  • Rao Muhammad Anwer
  • Hisham Cholakkal
  • Fahad Shahbaz Khan
  • Yanwei Pang
  • Ling Shao
Document Type
Article
Publication Date
7-29-2020
Abstract

Single-stage instance segmentation approaches have recently gained popularity due to their speed and simplicity, but are still lagging behind in accuracy, compared to two-stage methods. We propose a fast single-stage instance segmentation method, called SipMask, that preserves instance-specific spatial information by separating mask prediction of an instance to different sub-regions of a detected bounding-box. Our main contribution is a novel light-weight spatial preservation (SP) module that generates a separate set of spatial coefficients for each sub-region within a bounding-box, leading to improved mask predictions. It also enables accurate delineation of spatially adjacent instances. Further, we introduce a mask alignment weighting loss and a feature alignment scheme to better correlate mask prediction with object detection. On COCO test-dev, our SipMask outperforms the existing single-stage methods. Compared to the state-of-the-art single-stage TensorMask, SipMask obtains an absolute gain of 1.0% (mask AP), while providing a four-fold speedup. In terms of real-time capabilities, SipMask outperforms YOLACT with an absolute gain of 3.0% (mask AP) under similar settings, while operating at comparable speed on a Titan Xp. We also evaluate our SipMask for real-time video instance segmentation, achieving promising results on YouTube-VIS dataset. The source code is available at this https URL.

Disciplines
Indexed in Scopus
No
Open Access
No
https://aps.arxiv.org/abs/2007.14772
Citation Information
Jiale Cao, Rao Muhammad Anwer, Hisham Cholakkal, Fahad Shahbaz Khan, et al.. "SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation." arXiv: Computer Vision and Pattern Recognition (2020)
Available at: http://works.bepress.com/hisham-cholakkal/10/