Table 1 Results of the quantitative evaluation of different methods on three benchmark datasets using the four metrics \(S_{\alpha }\), \(E_{\phi }\), \(F_{\beta }^{\omega }\), and \(M\). “\(\uparrow / \downarrow\)” indicates that bigger or smaller is better.

From: Camouflaged object detection via context and texture-aware hierarchical interaction

Baseline models	CAMO				COD10K				NC4K
Baseline models	\(S_{\alpha } \uparrow\)	\(E_{\phi } \uparrow\)	\(F_{\beta }^{\omega } \uparrow\)	\(M \downarrow\)	\(S_{\alpha } \uparrow\)	\(E_{\phi } \uparrow\)	\(F_{\beta }^{\omega } \uparrow\)	\(M \downarrow\)	\(S_{\alpha } \uparrow\)	\(E_{\phi } \uparrow\)	\(F_{\beta }^{\omega } \uparrow\)	\(M \downarrow\)
SINet₂₀⁵⁰	0.745	0.804	0.644	0.092	0.776	0.864	0.631	0.043	0.808	0.871	0.723	0.058
C2FNet₂₁³⁰	0.796	0.854	0.719	0.080	0.813	0.890	0.686	0.036	0.838	0.897	0.762	0.049
TINet₂₁⁴⁸	0.781	0.836	0.678	0.087	0.793	0.861	0.635	0.042	0.829	0.879	0.734	0.055
JCSOD₂₁¹⁵	0.800	0.859	0.728	0.073	0.809	0.884	0.684	0.035	0.842	0.898	0.771	0.047
LSR₂₁¹¹	0.787	0.838	0.696	0.080	0.804	0.880	0.673	0.037	0.840	0.895	0.766	0.048
R-MGL₂₁¹³	0.775	0.812	0.673	0.088	0.814	0.852	0.666	0.035	0.833	0.867	0.740	0.052
PFNet₂₁²⁹	0.782	0.841	0.695	0.085	0.800	0.877	0.660	0.040	0.829	0.887	0.745	0.053
C2FNet-V2₂₂⁵⁵	0.799	0.859	0.730	0.077	0.811	0.887	0.691	0.036	0.840	0.896	0.770	0.048
ERRNet₂₂⁵⁶	0.779	0.842	0.679	0.085	0.786	0.867	0.630	0.043	0.827	0.887	0.737	0.054
TPRNet₂₂³²	0.807	0.861	0.725	0.074	0.817	0.887	0.683	0.036	0.846	0.898	0.768	0.048
FAPNet₂₂²⁶	0.815	0.865	0.734	0.076	0.822	0.888	0.694	0.036	0.851	0.899	0.775	0.047
BGNet₂₂⁵⁸	0.812	0.870	0.749	0.073	0.831	0.901	0.722	0.033	0.851	0.907	0.788	0.044
PreyNet₂₂²⁸	0.790	0.842	0.708	0.077	0.813	0.881	0.697	0.034	0.834	0.887	0.763	0.050
ZoomNet₂₂²⁷	0.820	0.877	0.752	0.066	0.838	0.888	0.729	0.029	0.853	0.896	0.784	0.043
SINetV2₂₂⁵⁰	0.820	0.882	0.743	0.070	0.815	0.887	0.680	0.037	0.847	0.903	0.770	0.048
DGNet₂₃¹⁹	0.839	0.901	0.769	0.057	0.822	0.896	0.693	0.033	0.857	0.911	0.784	0.042
FSPNet₂₃⁵⁹	0.856	0.899	0.799	0.050	0.851	0.895	0.735	0.026	0.879	0.915	0.816	0.035
Camoformer-C₂₄⁶⁰	0.859	0.913	0.812	0.050	0.860	0.926	0.770	0.024	0.883	0.933	0.788	0.032
MSCNet₂₄⁶¹	0.873	0.927	0.826	0.046	0.861	0.925	0.770	0.025	0.884	0.931	0.833	0.033
CINet₂₄⁶²	0.847	0.899	0.794	0.055	0.841	0.914	0.744	0.028	0.868	0.924	0.815	0.037
SDRNet₂₄⁶³	0.872	0.924	0.826	0.049	0.871	0.924	0.785	0.023	0.889	0.934	0.842	0.032
MIGNet₂₅⁶⁴	0.875	0.926	0.831	0.044	0.861	0.926	0.768	0.025	0.885	0.930	0.836	0.033
Ours	0.882	0.931	0.842	0.044	0.869	0.930	0.785	0.023	0.890	0.935	0.844	0.032

Back to article page

Table 1 Results of the quantitative evaluation of different methods on three benchmark datasets using the four metrics \(S_{\alpha }\), \(E_{\phi }\), \(F_{\beta }^{\omega }\), and \(M\). “\(\uparrow / \downarrow\)” indicates that bigger or smaller is better.

Search

Quick links