郑州大学学报（工学版）2025，Vol.46Issue(5)：9-17,9.DOI:10.13705/j.issn.1671-6833.2025.02.009
用于伪装目标检测的边缘-纹理引导增强网络
Edge-texture Guided Enhancement Network for Camouflaged Object Detection
摘要
Abstract
Camouflaged object detection(COD)is facing significant challenges due to the high similarity between target objects and their background,such as blurred edge predictions,incomplete detection results,and interfer-ence caused by the insufficient use of edge and texture information.To address the issues of current COD,a novel edge-texture guided enhancement network(ETGENet)was proposed to further improve the performance of COD through explicit and sufficient edge-texture guidance strategies.Firstly,a key feature guided enhancement module(FGEM)was used in ETGENet,which could use parallel feature refinement branches to process and enhance ob-ject features.The guide branch could obtain object features by guiding attention correlation with edge and texture cues to enhance the network's understanding of object details and suppress noise interference.While the self-en-hancement branch could use the self-attention mechanism to refine the characteristics of camouflaged objects from a global perspective.Secondly,a feature interaction fusion module(FIFM)was also proposed to progressively fuse adjacent features.FIFM could utilize the attention interaction mechanism and weighted fusion strategy to learn com-plementary information between features to generate more complete predicted map.Experiments on three public datasets CAMO,COD10K,and NC4K demonstrate that the proposed network outperformed state-of-the-art methods in the field across metrics such as structure measure S,adaptive enhanced matching measure E,weighted F-meas-ure,and mean absolute error M.Notably,on the largest test set,NC4K,the weighted F-measure surpassed the best-performing method among the 12 advanced COD methods,FSPNet,by 2.2 percentage points.关键词
伪装目标检测/边缘信息/纹理信息/特征引导/特征交互Key words
camouflaged object detection/edge information/texture information/feature guide/feature interaction分类
信息技术与安全科学引用本文复制引用
魏明军,陈晓茹,刘铭,刘亚志,李辉..用于伪装目标检测的边缘-纹理引导增强网络[J].郑州大学学报（工学版）,2025,46(5):9-17,9.基金项目
国家自然科学基金资助项目(52074126) （52074126）
河北省高等学校科学技术研究项目(ZD2022102) （ZD2022102）
