Table 4 Comparison of performance...

Table 4

Comparison of performance metrics between proposed and benchmark methods on the COD10K dataset. Only models with more than 50G Multiply-Accumulate Operations (MACs) were considered. The top-performing method for each metric on each dataset is highlighted in bold, while the second-best method is underscored.

Model	Pub/Year	Input	s_α ↑	$F_{β}^{w} ↑$	M↑	$E_{ϕ}^{m n} ↑$	Para.	MACs
R-MGL [39]	CVPR’21	473²	0.833	0.740	0.052	0.867	67.64M	249.89G
S-MGL [39]	CVPR’21	473²	0.829	0.731	0.055	0.863	63.60M	236.60G
UGTR [36]	ICCV’21	473²	0.839	0.747	0.052	0.874	48.87M	127.12G
BAS [30]	arXiv’21	288²	0.817	0.732	0.058	0.859	87.06M	161.19G
NCHIT [40]	CVIU’22	288²	0.830	0.710	0.058	0.851	-	-
OCENet [23]	WACV’22	480²	0.853	0.785	0.045	0.902	60.31M	59.70G
BGNet [33]	IJCAI’22	416²	0.851	0.788	0.044	0.907	79.85M	58.45G
PreyNet [43]	MM’22	448²	0.834	0.763	0.050	0.887	38.53M	58.10G
ZoomNet [29]	CVPR’22	384²	0.853	0.784	0.043	0.896	32.38M	95.50G
FDNet [45]	CVPR’22	416²	0.834	0.750	0.052	0.893	-	-
CamoFormer-C [38]	arXiv’23	384²	0.883	0.834	0.032	0.933	96.69M	50.77G
CamoFormer-R [38]	arXiv’23	384²	0.855	0.788	0.042	0.900	54.25M	78.85G
PopNet [35]	arXiv’23	512²	0.861	0.802	0.042	0.909	188.05M	154.88G
GreenCOD-D3-1000	-	672²	0.815	0.756	0.049	0.884	16.83M	13.70G
GreenCOD-D3-10000	-	672²	0.823	0.766	0.047	0.892	17.62M	15.06G
GreenCOD-D6-1000	-	672²	0.820	0.763	0.047	0.891	17.50M	13.78G
GreenCOD-D6-10000	-	672²	0.827	0.772	0.046	0.893	24.34M	16.22G

Model	Pub/Year	Input	s_α ↑	$F_{β}^{w} ↑$	M↑	$E_{ϕ}^{m n} ↑$	Para.	MACs
R-MGL [39]	CVPR’21	473²	0.833	0.740	0.052	0.867	67.64M	249.89G
S-MGL [39]	CVPR’21	473²	0.829	0.731	0.055	0.863	63.60M	236.60G
UGTR [36]	ICCV’21	473²	0.839	0.747	0.052	0.874	48.87M	127.12G
BAS [30]	arXiv’21	288²	0.817	0.732	0.058	0.859	87.06M	161.19G
NCHIT [40]	CVIU’22	288²	0.830	0.710	0.058	0.851	-	-
OCENet [23]	WACV’22	480²	0.853	0.785	0.045	0.902	60.31M	59.70G
BGNet [33]	IJCAI’22	416²	0.851	0.788	0.044	0.907	79.85M	58.45G
PreyNet [43]	MM’22	448²	0.834	0.763	0.050	0.887	38.53M	58.10G
ZoomNet [29]	CVPR’22	384²	0.853	0.784	0.043	0.896	32.38M	95.50G
FDNet [45]	CVPR’22	416²	0.834	0.750	0.052	0.893	-	-
CamoFormer-C [38]	arXiv’23	384²	0.883	0.834	0.032	0.933	96.69M	50.77G
CamoFormer-R [38]	arXiv’23	384²	0.855	0.788	0.042	0.900	54.25M	78.85G
PopNet [35]	arXiv’23	512²	0.861	0.802	0.042	0.909	188.05M	154.88G
GreenCOD-D3-1000	-	672²	0.815	0.756	0.049	0.884	16.83M	13.70G
GreenCOD-D3-10000	-	672²	0.823	0.766	0.047	0.892	17.62M	15.06G
GreenCOD-D6-1000	-	672²	0.820	0.763	0.047	0.891	17.50M	13.78G
GreenCOD-D6-10000	-	672²	0.827	0.772	0.046	0.893	24.34M	16.22G

[ViewLarge]