KepSalinst : Using Peripheral Points to Delineate Salient Instances

Jinpeng CHEN, Runmin CONG, Horace Ho Shing IP, Sam KWONG

Research output: Journal PublicationsJournal Article (refereed)peer-review

1 Citation (Scopus)

Abstract

Salient instance segmentation (SIS) is an emerging field that evolves from salient object detection (SOD), aiming at identifying individual salient instances using segmentation maps. Inspired by the success of dynamic convolutions in segmentation tasks, this article introduces a keypoints-based SIS network (KepSalinst). It employs multiple keypoints, that is, the center and several peripheral points of an instance, as effective geometrical guidance for dynamic convolutions. The features at peripheral points can help roughly delineate the spatial extent of the instance and complement the information inside the central features. To fully exploit the complementary components within these features, we design a differentiated patterns fusion (DPF) module. This ensures that the resulting dynamic convolutional filters formed by these features are sufficiently comprehensive for precise segmentation. Furthermore, we introduce a high-level semantic guided saliency (HSGS) module. This module enhances the perception of saliency by predicting a map for the input image to estimate a saliency score for each segmented instance. On four SIS datasets (ILSO, SOC, SIS10K, and COME15K), our KepSalinst outperforms all previous models qualitatively and quantitatively.
Original languageEnglish
Pages (from-to)1-14
Number of pages14
JournalIEEE Transactions on Cybernetics
DOIs
Publication statusE-pub ahead of print - 9 Nov 2023

Bibliographical note

Publisher Copyright:
IEEE

Keywords

  • Dynamic convolution
  • Fuses
  • Head
  • Object detection
  • Remote sensing
  • Semantics
  • Task analysis
  • Urban areas
  • peripheral points
  • salient instance segmentation (SIS)

Fingerprint

Dive into the research topics of 'KepSalinst : Using Peripheral Points to Delineate Salient Instances'. Together they form a unique fingerprint.

Cite this