Video Object Segmentation using Point-based Memory Network

Gao，Mingqi1,2; Han，Jungong2,3; Zheng，Feng1; Yu，James J.Q.1; Montana，Giovanni2

2023-02-01

10.1016/j.patcog.2022.109073

PATTERN RECOGNITION   Impact Factor & Quartile

0031-3203

1873-5142

Recent years have witnessed the prevalence of memory-based methods for Semi-supervised Video Object Segmentation (SVOS) which utilise past frames efficiently for label propagation. When conducting feature matching, fine-grained multi-scale feature matching has typically been performed using all query points, which inevitably results in redundant computations and thus makes the fusion of multi-scale results ineffective. In this paper, we develop a new Point-based Memory Network, termed as PMNet, to perform fine-grained feature matching on hard samples only, assuming that easy samples can already obtain satisfactory matching results without the need for complicated multi-scale feature matching. Our approach first generates an uncertainty map from the initial decoding outputs. Next, the fine-grained features at uncertain locations are sampled to match the memory features on the same scale. Finally, the matching results are further decoded to provide a refined output. The point-based scheme works with the coarsest feature matching in a complementary and efficient manner. Furthermore, we propose an approach to adaptively perform global or regional matching based on the motion history of memory points, making our method more robust against ambiguous backgrounds. Experimental results on several benchmark datasets demonstrate the superiority of our proposed method over state-of-the-art methods.

Adaptive matching module Point-based feature matching Video object segmentation

SCI

English

First

Computer Science ; Engineering

Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic

WOS:000927839900004

ELSEVIER SCI LTD

ENGINEERING

2-s2.0-85139349829

Scopus

1.Department of Computer Science and Engineering,Southern University of Science and Technology,Shenzhen,518055,China
2.WMG Data Science,University of Warwick,Coventry,CV4 7AL,United Kingdom
3.Department of Computer Science,Aberystwyth University,Aberystwyth,SY23 3DB,United Kingdom

Gao，Mingqi,Han，Jungong,Zheng，Feng,et al. Video Object Segmentation using Point-based Memory Network[J]. PATTERN RECOGNITION,2023,134.

Gao，Mingqi,Han，Jungong,Zheng，Feng,Yu，James J.Q.,&Montana，Giovanni.(2023).Video Object Segmentation using Point-based Memory Network.PATTERN RECOGNITION,134.

Gao，Mingqi,et al."Video Object Segmentation using Point-based Memory Network".PATTERN RECOGNITION 134(2023).