Loading [a11y]/accessibility-menu.js
Pixel Offset Regression (POR) for Single-shot Instance Segmentation | IEEE Conference Publication | IEEE Xplore

Pixel Offset Regression (POR) for Single-shot Instance Segmentation


Abstract:

State-of-the-art instance segmentation methods including Mask-RCNN and MNC are multi-shot, as multiple region of interest (ROI) forward passes are required to distinguish...Show More

Abstract:

State-of-the-art instance segmentation methods including Mask-RCNN and MNC are multi-shot, as multiple region of interest (ROI) forward passes are required to distinguish candidate regions. Multi-shot architectures usually achieve good performance on public benchmarks. However, hundreds of ROI forward passes in sequel limits their running efficiency, which is a critical point in several utilities such as vehicle surveillance. As such, we arrange our focus on seeking a well trade-off between performance and efficiency. In this paper, we introduce a novel Pixel Offset Regression (POR) scheme which can simply extend single-shot object detector to single-shot instance segmentation system, i.e., segmenting all instances in a single pass. Our framework is based on VGG161 with following four parts: (1) a single-shot detection branch to generate object detections, (2) a segmentation branch to estimate foreground masks, (3) a pixel offset regression branch to effectively estimate the distance and orientation from each pixel to the respective object center and (4) a merging process combining output of each branch to obtain instances. Our framework is evaluated on Berkeley-BDD, KITTI and PASCAL VOC2012 validation set, with comparison against several VGG16 based multi-shot methods. Without whistles and bells, our framework exhibits decent performance, which shows good potential for fast speed required applications.
Date of Conference: 27-30 November 2018
Date Added to IEEE Xplore: 14 February 2019
ISBN Information:
Conference Location: Auckland, New Zealand

Contact IEEE to Subscribe

References

References is not available for this document.