Dichotomous Image Segmentation On Dis Te1

E-measure

HCE

MAE

S-Measure

max F-Measure

weighted F-measure

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

比較表

モデル名	E-measure	HCE	MAE	S-Measure	max F-Measure	weighted F-measure
concealed-object-detection	0.791	274	0.094	0.727	0.644	0.558
icnet-for-real-time-semantic-segmentation-on	0.784	234	0.095	0.716	0.631	0.535
camouflaged-object-segmentation-with	0.786	253	0.094	0.722	0.646	0.552
patch-depth-fusion-dichotomous-image	0.927	-	0.031	0.899	0.890	0.846
hyperseg-patch-wise-hypernetwork-for-real	0.803	205	0.082	0.761	0.695	0.597
rethinking-bisenet-for-real-time-semantic	0.798	249	0.090	0.723	0.648	0.562
u-net-convolutional-networks-for-biomedical	0.750	233	0.106	0.716	0.625	0.514
bisenet-bilateral-segmentation-network-for	0.741	288	0.108	0.695	0.595	0.474
suppress-and-balance-a-simple-gated-network	0.766	230	0.099	0.701	0.620	0.517
190807919	0.797	262	0.088	0.742	0.668	0.579
rethinking-atrous-convolution-for-semantic	0.772	234	0.102	0.694	0.601	0.506
searching-for-mobilenetv3	0.818	274	0.083	0.740	0.669	0.595
f3net-fusion-feedback-and-focus-for-salient	0.783	244	0.095	0.721	0.640	0.549
revisiting-image-pyramid-structure-for-high	0.894	110	0.045	0.873	0.845	0.788
pyramid-scene-parsing-network	0.791	267	0.089	0.725	0.645	0.557
highly-accurate-dichotomous-image	0.820	149	0.074	0.787	0.740	0.662
u-2-net-going-deeper-with-nested-u-structure	0.801	224	0.083	0.760	0.694	0.601
multi-view-aggregation-network-for	0.911	104	0.037	0.879	0.873	0.823
revisiting-image-pyramid-structure-for-high	-	148	-	0.862	0.834	-
bilateral-reference-for-high-resolution	0.908	106	0.038	0.882	0.855	0.814
global-context-aware-progressive-aggregation	0.750	271	0.103	0.705	0.598	0.495
basnet-boundary-aware-salient-object	0.801	220	0.084	0.754	0.688	0.595