计算机科学
背景(考古学)
任务(项目管理)
比例(比率)
特征(语言学)
对象(语法)
骨干网
人工智能
相似性(几何)
目标检测
计算机视觉
模式识别(心理学)
图像(数学)
工程类
计算机网络
地理
语言学
哲学
地图学
考古
系统工程
出处
期刊:IEEE transactions on emerging topics in computational intelligence
[Institute of Electrical and Electronics Engineers]
日期:2023-01-01
卷期号:: 1-13
被引量:1
标识
DOI:10.1109/tetci.2023.3299305
摘要
Camouflaged object detection (COD), with the task of separating the camouflaged object from its color/texture similar background, has been widely used in the fields of medical diagnosis and military reconnaissance. However, the COD task is still a challenging problem due to two main difficulties: large scale-variation for different camouflaged objects, and extreme similarity between the camouflaged object and its background. To address these problems, a cross-level interaction network based on scale-aware augmentation (CINet) for the COD task is proposed. Specifically, a scale-aware augmentation module (SAM) is firstly designed to perceive the scales information of the camouflaged object by calculating an optimal receptive field. Furthermore, a cross-level interaction module (CLIM) is proposed to facilitate the interaction of scale information at all levels, and the context of the feature maps is enriched accordingly. Finally, with the purpose of fully utilizing these features, we design a dual-branch feature decoder (DFD) to strengthen the connection between the predictions at each level. Extensive experiments performed on four COD datasets, e.g., CHAMELEON, CAMO, COD10K, and NC4K, demonstrate the superiority of the proposed CINet compared with 21 existing state-of-the-art methods.
科研通智能强力驱动
Strongly Powered by AbleSci AI