摘要
当前,显著性目标检测技术正在迅速发展,但仍然存在一些问题亟待解决.大多数现有的显著性目标检测方法在处理高分辨率图像任务时,存在计算资源需求过高或者检测质量较差等问题.其次,许多现有算法采用的传统卷积操作缺乏针对性,无法有效增强边缘细节特征,导致边缘分割模糊不清.为了在降低算力消耗的同时提高物体边缘分割质量,并提升小尺度目标的检测性能,提出了基于边缘增强的宽解码器显著性目标检测方法.采用残差网络和Swin Transformer组合结构作为特征编码器,以降低算力消耗.并且将传统卷积替换为差分卷积模块,通过多种不同类型的差分卷积并行使用,从图像中提取了更加丰富的边缘信息.设计了多尺度注意力模块,对4层不同尺度特征进行注意力计算,以更好地关注不同大小的目标.此外,采用含有大卷积核的多级宽解码器,对融合特征进行长距离的上下文建模,减少冗余信息,进一步提升了网络的检测性能.
Salient object detection is developing rapidly.However,several critical challenges remain.Most existing methods struggle with high-resolution images due to either excessive computational demands or suboptimal detection quality.In addition,traditional convolutional operations commonly used in current algorithms lack targeted enhancement,resulting in inadequate edge detail extraction and blurred object boundaries.To address these limitations,this study proposes a salient object detection method based on an edge-enhanced wide decoder,which improves edge segmentation accuracy and enhances small-scale object detection while reducing computational overhead.A hybrid feature encoder combining a residual network and a Swin Transformer is employed to lower computational overhead.Traditional convolutions are replaced with a differential convolution module,where multiple types of differential convolutions are executed in parallel to extract richer edge information.A multi-scale attention module is incorporated to compute attention across four hierarchical feature layers,enabling better focus on objects of varying sizes.In addition,a multilevel wide decoder with large convolutional kernels is utilized to conduct long-range contextual modeling of fused features,effectively reducing redundant information and further boosting detection performance.Code will be released at https://github.com/wapitier/EEWDNet.
作者
童彪
宋晓宁
华阳
张文杰
吴小俊
TONG Biao;SONG Xiao-Ning;HUA Yang;ZHANG Wen-Jie;WU Xiao-Jun(School of Artificial Intelligence and Computer Science,Jiangnan University,Wuxi 214100,China)
出处
《软件学报》
北大核心
2026年第2期953-968,共16页
Journal of Software
基金
国家重点研发计划(2023YFF1105102,2023YFF1105105)
国家社会科学基金(21&ZD166)
国家自然科学基金(61876072)
江苏省自然科学基金(BK20221535)。
关键词
显著性目标检测
边缘增强
差分卷积
salient object detection
edge enhancement
difference convolution
