Adaptive Graph Convolution Module for Salient Object Detection

Salient object detection (SOD) is a task that involves identifying and segmenting the most visually prominent object in an image. Existing solutions can accomplish this using a multi-scale feature fusion mechanism to detect the global context of an image. However, as there is no consideration of the...

Full description

Saved in:
Bibliographic Details
Published in2023 IEEE International Conference on Image Processing (ICIP) pp. 1395 - 1399
Main Authors Lee, Yongwoo, Lee, Minhyeok, Cho, Suhwan, Lee, Sangyoun
Format Conference Proceeding
LanguageEnglish
Published IEEE 08.10.2023
Subjects
Adaptation models
Convolution
Global context
Graph convolutional neural networks
Image edge detection
Image segmentation
Object detection
Prototypes
Salient object detection
Semantics
Online AccessGet full text

Cover

More Information
Summary:Salient object detection (SOD) is a task that involves identifying and segmenting the most visually prominent object in an image. Existing solutions can accomplish this using a multi-scale feature fusion mechanism to detect the global context of an image. However, as there is no consideration of the structures in the image nor the relations between distant pixels, conventional methods cannot deal with complex scenes effectively. In this paper, we propose an adaptive graph convolution module (AGCM) to overcome these limitations. Prototype features are initially extracted from the input image using a learnable region generation layer that spatially groups features in the image. The prototype features are then refined by propagating information between them based on a graph architecture, where each feature is regarded as a node. Experimental results show that the proposed AGCM dramatically improves the SOD performance both quantitatively and quantitatively.
DOI:10.1109/ICIP49359.2023.10222238