Timezone: »

Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation
Yuxi Li · Ning Xu · Jinlong Peng · John See · Weiyao Lin

Tue Dec 08 09:00 AM -- 11:00 AM (PST) @ Poster Session 1 #214

In this paper, we take attempt to incorporate the cyclic mechanism with the vision task of semi-supervised video object segmentation. By resorting to the accurate reference mask of the first frame, we try to mitigate the error propagation problem in most of current video object segmentation pipelines. Firstly, we propose a cyclic scheme for offline training of segmentation networks. Then, we extend the offline pipeline to an online method by introducing a simple gradient correction module while keeping high efficiency as other offline methods. Finally we develop cycle effective receptive field (cycle-ERF) from gradient correction to provide a new perspective for analyzing object-specific regions of interests. We conduct comprehensive experiments on benchmarks of DAVIS17 and Youtube-VOS, demonstrating that our introduced cyclic mechanism is helpful to boost the segmentation quality.

Author Information

Yuxi Li (Shanghai Jiao Tong University)
Ning Xu (Adobe Research)
Jinlong Peng (Tencent Youtu Lab)
John See (Multimedia University)
Weiyao Lin (Shanghai Jiao Tong university)

More from the Same Authors