Curiosity-Driven Camouflaged Object Segmentation

Camouflaged object segmentation refers to the task of accurately extracting objects that are seamlessly integrated within their surrounding environment. Existing deep-learning methods frequently encounter challenges in accurately segmenting camouflaged objects, particularly in capturing their comple...

Full description

Saved in:
Bibliographic Details
Main Authors: Mengyin Pang, Meijun Sun, Zheng Wang
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/1/173
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850117193571762176
author Mengyin Pang
Meijun Sun
Zheng Wang
author_facet Mengyin Pang
Meijun Sun
Zheng Wang
author_sort Mengyin Pang
collection DOAJ
description Camouflaged object segmentation refers to the task of accurately extracting objects that are seamlessly integrated within their surrounding environment. Existing deep-learning methods frequently encounter challenges in accurately segmenting camouflaged objects, particularly in capturing their complete and intricate details. To this end, we propose a novel method based on the Curiosity-Driven network, which is motivated by the innate human tendency for curiosity when encountering ambiguous regions and the subsequent drive to explore and observe objects’ details. Specifically, the proposed fusion bridge module aims to exploit the model’s inherent curiosity to fuse these features extracted by the dual-branch feature encoder to capture the complete details of the object. Then, drawing inspiration from curiosity, the curiosity-refinement module is proposed to progressively refine the initial predictions by exploring unknown regions within the object’s surrounding environment. Notably, we develop a novel curiosity-calculation operation to discover and remove curiosity, leading to accurate segmentation results. Extensive quantitative and qualitative experiments demonstrate that the proposed model significantly outperforms the existing competitors on three challenging benchmark datasets. Compared with the recently proposed state-of-the-art method, our model achieves performance gains of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1.80</mn><mo>%</mo></mrow></semantics></math></inline-formula> on average for <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>S</mi><mi>α</mi></msub></semantics></math></inline-formula>. Moreover, our model can be extended to the polyp and industrial defects segmentation tasks, validating its robustness and effectiveness.
format Article
id doaj-art-c7bbe3ccf379433781efdfe11aa354c9
institution OA Journals
issn 2076-3417
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-c7bbe3ccf379433781efdfe11aa354c92025-08-20T02:36:08ZengMDPI AGApplied Sciences2076-34172024-12-0115117310.3390/app15010173Curiosity-Driven Camouflaged Object SegmentationMengyin Pang0Meijun Sun1Zheng Wang2College of Intelligence and Computing, Tianjin University, Tianjin 300350, ChinaCollege of Intelligence and Computing, Tianjin University, Tianjin 300350, ChinaCollege of Intelligence and Computing, Tianjin University, Tianjin 300350, ChinaCamouflaged object segmentation refers to the task of accurately extracting objects that are seamlessly integrated within their surrounding environment. Existing deep-learning methods frequently encounter challenges in accurately segmenting camouflaged objects, particularly in capturing their complete and intricate details. To this end, we propose a novel method based on the Curiosity-Driven network, which is motivated by the innate human tendency for curiosity when encountering ambiguous regions and the subsequent drive to explore and observe objects’ details. Specifically, the proposed fusion bridge module aims to exploit the model’s inherent curiosity to fuse these features extracted by the dual-branch feature encoder to capture the complete details of the object. Then, drawing inspiration from curiosity, the curiosity-refinement module is proposed to progressively refine the initial predictions by exploring unknown regions within the object’s surrounding environment. Notably, we develop a novel curiosity-calculation operation to discover and remove curiosity, leading to accurate segmentation results. Extensive quantitative and qualitative experiments demonstrate that the proposed model significantly outperforms the existing competitors on three challenging benchmark datasets. Compared with the recently proposed state-of-the-art method, our model achieves performance gains of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1.80</mn><mo>%</mo></mrow></semantics></math></inline-formula> on average for <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>S</mi><mi>α</mi></msub></semantics></math></inline-formula>. Moreover, our model can be extended to the polyp and industrial defects segmentation tasks, validating its robustness and effectiveness.https://www.mdpi.com/2076-3417/15/1/173deep-learningcamouflaged object segmentationcuriosity-driven
spellingShingle Mengyin Pang
Meijun Sun
Zheng Wang
Curiosity-Driven Camouflaged Object Segmentation
Applied Sciences
deep-learning
camouflaged object segmentation
curiosity-driven
title Curiosity-Driven Camouflaged Object Segmentation
title_full Curiosity-Driven Camouflaged Object Segmentation
title_fullStr Curiosity-Driven Camouflaged Object Segmentation
title_full_unstemmed Curiosity-Driven Camouflaged Object Segmentation
title_short Curiosity-Driven Camouflaged Object Segmentation
title_sort curiosity driven camouflaged object segmentation
topic deep-learning
camouflaged object segmentation
curiosity-driven
url https://www.mdpi.com/2076-3417/15/1/173
work_keys_str_mv AT mengyinpang curiositydrivencamouflagedobjectsegmentation
AT meijunsun curiositydrivencamouflagedobjectsegmentation
AT zhengwang curiositydrivencamouflagedobjectsegmentation