Table 2 Results of the quantitative evaluation of different ablation models on three benchmark datasets using the four metrics \(S_{\alpha }\), \(E_{\phi }\), \(F_{\beta }^{\omega }\) and \(M\). “\({ \uparrow \mathord{\left/ {\vphantom { \uparrow \downarrow }} \right. \kern-0pt} \downarrow }\)” indicates that bigger or smaller is better.

Baseline models	CAMO				COD10K				NC4K
Baseline models	\(S_{\alpha } \uparrow\)	\(E_{\phi } \uparrow\)	\(F_{\beta }^{\omega } \uparrow\)	\(M \downarrow\)	\(S_{\alpha } \uparrow\)	\(E_{\phi } \uparrow\)	\(F_{\beta }^{\omega } \uparrow\)	\(M \downarrow\)	\(S_{\alpha } \uparrow\)	\(E_{\phi } \uparrow\)	\(F_{\beta }^{\omega } \uparrow\)	\(M \downarrow\)
Basic (M1)	0.854	0.902	0.771	0.059	0.836	0.898	0.692	0.034	0.870	0.915	0.783	0.042
Basic + MFAM (M2)	0.863	0.914	0.806	0.053	0.855	0.920	0.751	0.027	0.881	0.929	0.821	0.035
Basic + w/o HMIM (M3)	0.869	0.912	0.809	0.051	0.860	0.921	0.758	0.026	0.886	0.928	0.829	0.034
Basic + MFAM + w/o HMIM (M4)	0.878	0.930	0.835	0.045	0.867	0.928	0.780	0.024	0.889	0.936	0.842	0.032
Basic + HMIM (M5)	0.877	0.928	0.833	0.046	0.867	0.927	0.778	0.024	0.889	0.935	0.841	0.032
Basic + HMIM + MFAM (M6)	0.882	0.931	0.842	0.044	0.869	0.930	0.785	0.023	0.890	0.935	0.844	0.032

Quick links

Search