Generic and attribute-specific deep representations for maritime vessels

Table 5 Vessel attribute classification performance of generic and attribute-specific representations, calculated for four attributes on 158,850 images of IMO testing set

Classified attribute	Employed representation	Top 1 accuracy	Top 2 accuracy	Top 3 accuracy	Top 4 accuracy	Top 5 accuracy
Draught	Generic model + SVM	0.1302	0.3104	0.4432	0.5506	0.6320
Gross tonnage	Generic model + SVM	0.4755	0.6393	0.7418	0.8178	0.8678
Length	Generic model + SVM	0.4539	0.6345	0.7317	0.8019	0.8510
Summer deadweight	Generic model + SVM	0.4304	0.6209	0.7310	0.7998	0.8525
Draught	Attribute-specific trained CNN	0.1834	0.4159	0.5761	0.6884	0.7774
Gross tonnage	Attribute-specific trained CNN	0.5515	0.7492	0.8556	0.9131	0.9454
Length	Attribute-specific trained CNN	0.5289	0.7266	0.8257	0.8896	0.9328
Summer deadweight	Attribute-specific trained CNN	0.5155	0.7364	0.8317	0.8938	0.9288