首页|Weakly-supervised instance co-segmentation via tensor-based salient co-peak search

Weakly-supervised instance co-segmentation via tensor-based salient co-peak search

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
Instance co-segmentation aims to segment the co-occurrent instances among two images.This task heavily relies on instance-related cues provided by co-peaks,which are generally estimated by exhaustively exploiting all paired candidates in point-to-point patterns.However,such patterns could yield a high number of false-positive co-peaks,resulting in over-segmentation whenever there are mutual occlusions.To tackle with this issue,this paper proposes an instance co-segmentation method via tensor-based salient co-peak search(TSCPS-ICS).The proposed method explores high-order correlations via triple-to-triple matching among feature maps to find reliable co-peaks with the help of co-saliency detection.The proposed method is shown to capture more accurate intra-peaks and inter-peaks among feature maps,reducing the false-positive rate of co-peak search.Upon having accurate co-peaks,one can efficiently infer responses of the targeted instance.Experiments on four benchmark datasets validate the superior performance of the proposed method.

weakly-supervisedco-segmentationco-peaktensor matchingdeep networkinstance segmentation

Wuxiu QUAN、Yu HU、Tingting DAN、Junyu LI、Yue ZHANG、Hongmin CAI

展开 >

School of Computer Science,Guangdong Polytechnic Normal University,Guangzhou 510665,China

School of Computer Science and Engineering,South China University of Technology,Guangzhou 510006,China

国家自然科学基金国家自然科学基金Key-Area Research and Development of Guangdong ProvinceKey-Area Research and Development of Guangdong Province国家重点研发计划Key-Area Research and Development Program of Guangzhou City

U21A20520621721122022A05050500142020B11111900012022YFE0112200202206030009

2024

10.1007/s11704-022-2468-8

计算机科学前沿
高等教育出版社

计算机科学前沿

CSTPCDEI
影响因子：0.303
ISSN：2095-2228
年,卷(期)：2024.18(2)
  • 42