KepSalinst: Using Peripheral Points to Delineate Salient Instances

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...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on cybernetics 2024-06, Vol.54 (6), p.3392-3405
Main Authors: Chen, Jinpeng, Cong, Runmin, Ip, Horace Ho Shing, Kwong, Sam
Format: Article
Language:English
Subjects:
Dynamic convolution
Fuses
Instance segmentation
Modules
Object detection
Object recognition
peripheral points
Remote sensing
Salience
Saliency detection
salient instance segmentation (SIS)
Semantics
Urban areas
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2168-2267
2168-2275
DOI:10.1109/TCYB.2023.3326165