Salient Object Detection On Duts Te

评估指标

MAE

S-Measure

max F-measure

mean E-Measure

mean F-Measure

评测结果

各个模型在此基准测试上的表现结果

						Paper Title	Repository
UCF	0.116	-	0.771	-	-	Learning Uncertain Convolutional Features for Accurate Saliency Detection
DCL	0.081	-	0.786	-	-	Deep Contrast Learning for Salient Object Detection	-
Amulet	0.075	-	0.773	-	-	Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection
DHS	0.065	-	0.815	-	-	DHSNet: Deep Hierarchical Saliency Network for Salient Object Detection	-
DSS	0.065	-	0.813	-	-	Deeply supervised salient object detection with short connections
NLDF	0.065	-	0.816	-	-	Non-Local Deep Features for Salient Object Detection	-
MSR	0.062	-	0.824	-	-	Instance-Level Salient Object Segmentation	-
SRM	0.058	-	0.826	-	-	A Stagewise Refinement Model for Detecting Salient Objects in Images	-
PAGR	0.055	-	0.854	-	-	Progressive Attention Guided Recurrent Network for Salient Object Detection	-
PiCANet	0.050	0.842	0.863	0.853	0.757	PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection
HybridSOD	0.05	0.837	-	-	-	A Weakly Supervised Learning Framework for Salient Object Detection via Hybrid Labels
DGRL	0.049	0.846	0.828	0.887	0.790	Detect Globally, Refine Locally: A Novel Approach to Saliency Detection	-
CFDN	0.048	0.871	0.859	-	-	Saliency Detection via Global Context Enhanced Feature Fusion and Edge Weighted Loss	-
BASNet	0.047	0.876	-	0.896	0.823	BASNet: Boundary-Aware Salient Object Detection	-
M3Net-R	0.036	0.897	-	-	-	M$^3$Net: Multilevel, Mixed and Multistage Attention Network for Salient Object Detection
PoolNet (VGG-16)	0.036	-	0.892	-	-	A Simple Pooling-Based Design for Real-Time Salient Object Detection
TRACER-(ResNet50)	0.035	-	-	-	-	TRACER: Extreme Attention Guided Salient Object Tracing Network
UCNet-CVAE	0.034	0.888	-	0.927	0.860	Uncertainty Inspired RGB-D Saliency Detection
CPDR-L	0.034	-	-	0.931	0.853	CPDR: Towards Highly-Efficient Salient Object Detection via Crossed Post-decoder Refinement	-
UCNet-ABP	0.034	0.890	-	0.931	0.864	Uncertainty Inspired RGB-D Saliency Detection

0 of 31 row(s) selected.