前景與背景交互融合網(wǎng)絡(luò)用于偽裝目標(biāo)檢測
打開文本圖片集
關(guān)鍵詞：偽裝目標(biāo)檢測；前景與背景信息；非局部注意力；特征交互；特征融合DOI：10.15938/j. jhust.2025.02.006中圖分類號：TP391.4 文獻(xiàn)標(biāo)志碼：A 文章編號：1007-2683（2025）02-0053-11
Abstract：Aiming atthe problem of incompletedetectionresultsand blurrededgedetailsincurrentcamouflagedobjectdetection （COD）methods，anovelForegroundand BackgroundInteractiveFusionNetwork（FBIFNet）wasproposed tofurtherimprovethe performanceofCODthroughjointexplorationofforegroundandbackgroundregions.FBFNetcontainsakeyBilateralInteractiveusion module（BIF），whichusesapairofcomplementaryatentionstoguidethenetwork tojointlyreasonaboutcamouflagedobjectsfrom bothforegroudandbackgrounddirectionsndalsoutilizesaninteractionstrategybasedonthebidirectionalatentionmechanismanda weighted fusionstrategytoleancomplementaryiformationbetweenforegroudandbackgroundIndition，anAtentionalCascaded Positioning module（ACP）isincluded，whichcanlocalizecamouflagedbjectsfromaglobalperspectiveandprovidemoreacurate foregroundandbackgroundguidanceforBIF.Withthetwoproposedmodules，F(xiàn)BIFNetcanmoreaccuratelydetectcamouflaged objects.Extensive experimentsonthree publicdatasets（CAMO，CODlOK，and NC4K）demonstrate thatthe proposednetwork outperforms state-of-the-art methods in related fields on four evaluation metrics.
Keywords：camouflagedbjectdetection；foregroundandbackgroundinformation;non-localatention；feature interaction；featur fusion
0 引言
偽裝是大自然中獵物為了躲避捕食者所進(jìn)化出的獨特能力。（剩余16994字）