AuthorsG. Ji, Y. Chou, D. Fan, G. Chen, H. Fu, D. Jha, and L. Shao
TitleProgressively Normalized Self-Attention Network for Video Polyp Segmentation
AfilliationMachine Learning
Project(s)Department of Holistic Systems
StatusPublished
Publication TypeProceedings, refereed
Year of Publication2021
Conference NameMedical Image Computing and Computer Assisted Intervention (MICCAI 2021)
VolumeLNCS, volume 12901
Pagination142-152
Publisher Springer
Keywordscolonoscopy, Normalized self-attention, Polyp segmentation
Abstract

Existing video polyp segmentation (VPS) models typically employ convolutional neural networks (CNNs) to extract features. However, due to their limited receptive fields, CNNs can not fully exploit the global temporal and spatial information in successive video frames, resulting in false positive segmentation results. In this paper, we propose the novel PNS-Net(Progressively Normalized Self-attention Net-work), which can efficiently learn representations from polyp videos with real-time speed (∼140fps) on a single RTX 2080 GPU and no post-processing. OurPNS-Netis based solely on a basic normalized self-attention block, equipping with recurrence and CNNs entirely. Experiments on challenging VPS datasets demonstrate that the proposed PMS-Netachieves state-of-the-art performance. We also conduct extensive experiments to study the effectiveness of the channel split, soft-attention, and progressive learning strategy. We find that our PNS-Networks well under different settings, making it a promising solution to the VPS task.

Citation Key27858

Contact person