PoolNet+: Exploring the Potential of Pooling for Salient Object Detection

We explore the potential of pooling techniques on the task of salient object detection by expanding its role in convolutional neural networks. In general, two pooling-based modules are proposed. A global guidance module (GGM) is first built based on the bottom-up pathway of the U-shape architecture,...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence Jg. 45; H. 1; S. 887 - 904
Hauptverfasser: Liu, Jiang-Jiang, Hou, Qibin, Liu, Zhi-Ang, Cheng, Ming-Ming
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States IEEE 01.01.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Applications programs
Artificial neural networks
Convolutional neural networks
Corresponding states
Edge detection
feature aggregation
Feature extraction
global guidance
Image edge detection
Image segmentation
mobile application
Mobile computing
Modules
Object detection
Object recognition
pooling techniques
Salience
Salient object detection
Semantics
Task analysis
ISSN:0162-8828, 1939-3539, 2160-9292, 1939-3539
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We explore the potential of pooling techniques on the task of salient object detection by expanding its role in convolutional neural networks. In general, two pooling-based modules are proposed. A global guidance module (GGM) is first built based on the bottom-up pathway of the U-shape architecture, which aims to guide the location information of the potential salient objects into layers at different feature levels. A feature aggregation module (FAM) is further designed to seamlessly fuse the coarse-level semantic information with the fine-level features in the top-down pathway. We can progressively refine the high-level semantic features with these two modules and obtain detail enriched saliency maps. Experimental results show that our proposed approach can locate the salient objects more accurately with sharpened details and substantially improve the performance compared with the existing state-of-the-art methods. Besides, our approach is fast and can run at a speed of 53 FPS when processing a <inline-formula><tex-math notation="LaTeX">300 \times 400</tex-math> <mml:math><mml:mrow><mml:mn>300</mml:mn><mml:mo>×</mml:mo><mml:mn>400</mml:mn></mml:mrow></mml:math><inline-graphic xlink:href="cheng-ieq1-3140168.gif"/> </inline-formula> image. To make our approach better applied to mobile applications, we take MobileNetV2 as our backbone and re-tailor the structure of our pooling-based modules. Our mobile version model achieves a running speed of 66 FPS yet still performs better than most existing state-of-the-art methods. To verify the generalization ability of the proposed method, we apply it to the edge detection, RGB-D salient object detection, and camouflaged object detection tasks, and our method achieves better results than the corresponding state-of-the-art methods of these three tasks. Code can be found at http://mmcheng.net/poolnet/ .
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0162-8828
1939-3539
2160-9292
1939-3539
DOI:10.1109/TPAMI.2021.3140168