Dichotomous Image Segmentation On Dis Te2

Métriques

E-measure

HCE

MAE

S-Measure

max F-Measure

weighted F-measure

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	E-measure	HCE	MAE	S-Measure	max F-Measure	weighted F-measure	Paper Title	Repository
U2Net	0.833	490	0.085	0.788	0.756	0.668	U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection
IS-Net	0.858	340	0.07	0.823	0.799	0.728	Highly Accurate Dichotomous Image Segmentation
BASNet	0.836	480	0.084	0.786	0.755	0.668	BASNet: Boundary-Aware Salient Object Detection	-
MBV3	0.856	600	0.083	0.777	0.743	0.672	Searching for MobileNetV3
GateNet	0.804	501	0.102	0.737	0.702	0.598	Suppress and Balance: A Simple Gated Network for Salient Object Detection
BiRefNet	0.935	265	0.035	0.904	0.898	0.863	Bilateral Reference for High-Resolution Dichotomous Image Segmentation
PSPNet	0.828	586	0.092	0.763	0.724	0.636	Pyramid Scene Parsing Network
DeeplabV3+	0.813	516	0.105	0.729	0.681	0.587	Rethinking Atrous Convolution for Semantic Image Segmentation
ICNet	0.826	512	0.095	0.759	0.716	0.627	ICNet for Real-Time Semantic Segmentation on High-Resolution Images
GCPANet	0.786	574	0.109	0.735	0.673	0.570	Global Context-Aware Progressive Aggregation Network for Salient Object Detection
InSPyReNet (HR scale)	-	255	-	0.905	0.894	-	Revisiting Image Pyramid Structure for High Resolution Salient Object Detection
F3Net	0.820	542	0.097	0.755	0.712	0.620	F3Net: Fusion, Feedback and Focus for Salient Object Detection
MVANet	0.944	251	0.030	0.915	0.916	0.874	Multi-view Aggregation Network for Dichotomous Image Segmentation
PDFNet	0.947	-	0.028	0.924	0.921	0.885	Patch-Depth Fusion: Dichotomous Image Segmentation via Fine-Grained Patch Strategy and Depth Integrity-Prior
HRNet	0.840	555	0.087	0.784	0.747	0.664	Deep High-Resolution Representation Learning for Visual Recognition
STDC	0.834	556	0.092	0.759	0.720	0.636	Rethinking BiSeNet For Real-time Semantic Segmentation
BSV1	0.781	621	0.111	0.740	0.680	0.564	BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
SINetV2	0.823	593	0.099	0.753	0.700	0.618	Concealed Object Detection
InSPyReNet	0.925	316	0.038	0.893	0.881	0.834	Revisiting Image Pyramid Structure for High Resolution Salient Object Detection
HySM	0.832	451	0.085	0.794	0.759	0.667	HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation

0 of 22 row(s) selected.