Visual Boundary Knowledge Translation for Foreground Segmentation

Authors

  • Zunlei Feng Zhejiang University
  • Lechao Cheng Zhejiang Lab
  • Xinchao Wang Stevens Institute of Technology
  • Xiang Wang Zhejiang University
  • Ya Jie Liu Zhejiang Lab
  • Xiangtong Du Jiangsu University of Science and Technology
  • Mingli Song Zhejiang University

Keywords:

Segmentation, Transfer/Adaptation/Multi-task/Meta/Automated Learning

Abstract

When confronted with objects of unknown types in an image, humans can effortlessly and precisely tell their visual boundaries. This recognition mechanism and underlying generalization capability seem to contrast to state-of-the-art image segmentation networks that rely on large-scale category-aware annotated training samples. In this paper, we make an attempt towards building models that explicitly account for visual boundary knowledge, in hope to reduce the training effort on segmenting unseen categories. Specifically, we investigate a new task termed as Boundary Knowledge Translation (BKT). Given a set of fully labeled categories, BKT aims to translate the visual boundary knowledge learned from the labeled categories, to a set of novel categories, each of which is provided only a few labeled samples. To this end, we propose a Translation Segmentation Network (Trans-Net), which comprises a segmentation network and two boundary discriminators. The segmentation network, combined with a boundary-aware self-supervised mechanism, is devised to conduct foreground segmentation, while the two discriminators work together in an adversarial manner to ensure an accurate segmentation of the novel categories under light supervision. Exhaustive experiments demonstrate that, with only tens of labeled samples as guidance, Trans-Net achieves close results on par with fully supervised methods.

Downloads

Published

2021-05-18

How to Cite

Feng, Z., Cheng, L., Wang, X., Wang, X., Liu, Y. J., Du, X., & Song, M. (2021). Visual Boundary Knowledge Translation for Foreground Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 35(2), 1334-1342. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16222

Issue

Section

AAAI Technical Track on Computer Vision I