Collaborative Content-Dependent Modeling: A Return to the Roots of Salient Object Detection

Salient object detection (SOD) aims to identify the most visually distinctive object(s) from each given image. Most recent progresses focus on either adding elaborative connections among different convolution blocks or introducing boundary-aware supervision to help achieve better segmentation, which...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing Vol. 32; pp. 4237 - 4246
Main Authors: Jiao, Siyu, Goel, Vidit, Navasardyan, Shant, Yang, Zongxin, Khachatryan, Levon, Yang, Yi, Wei, Yunchao, Zhao, Yao, Shi, Humphrey
Format: Journal Article
Language:English
Published: United States IEEE 2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Coders
Collaboration
content-dependent modeling
Context
Convolution
Decoding
Encoders-Decoders
Feature extraction
Head
Image segmentation
Modules
Object detection
Object recognition
Roots
Salience
Salient object detection
Task analysis
Transformers
ISSN:1057-7149, 1941-0042, 1941-0042
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Salient object detection (SOD) aims to identify the most visually distinctive object(s) from each given image. Most recent progresses focus on either adding elaborative connections among different convolution blocks or introducing boundary-aware supervision to help achieve better segmentation, which is actually moving away from the essence of SOD, i.e., distinctiveness/salience. This paper goes back to the roots of SOD and investigates the principles of how to identify distinctive object(s) in a more effective and efficient way. Intuitively, the salience of one object should largely depend on its global context within the input image. Based on this, we devise a clean yet effective architecture for SOD, named Collaborative Content-Dependent Networks (CCD-Net). In detail, we propose a collaborative content-dependent head whose parameters are conditioned on the input image's global context information. Within the content-dependent head, a hand-crafted multi-scale (HMS) module and a self-induced (SI) module are carefully designed to collaboratively generate content-aware convolution kernels for prediction. Benefited from the content-dependent head, CCD-Net is capable of leveraging global context to detect distinctive object(s) while keeping a simple encoder-decoder design. Extensive experimental results demonstrate that our CCD-Net achieves state-of-the-art results on various benchmarks. Our architecture is simple and intuitive compared to previous solutions, resulting in competitive characteristics with respect to model complexity, operating efficiency, and segmentation accuracy.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1057-7149
1941-0042
1941-0042
DOI:10.1109/TIP.2023.3293759