HyperAI超神経

プラットフォーム

Salient Object Detection On Ecssd

評価指標

MAE

mean E-Measure

mean 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

				Paper Title
DSS (Res2Net-50)	0.056	-	-	Res2Net: A New Multi-scale Backbone Architecture
HybridSOD	0.051	-	-	A Weakly Supervised Learning Framework for Salient Object Detection via Hybrid Labels
PoolNet (VGG-16)	0.038	-	-	A Simple Pooling-Based Design for Real-Time Salient Object Detection
BASNet	0.037	-	-	BASNet: Boundary-Aware Salient Object Detection
CPD-R (ResNet50)	0.037	-	-	Cascaded Partial Decoder for Fast and Accurate Salient Object Detection
UCNet-CVAE	0.035	-	-	Uncertainty Inspired RGB-D Saliency Detection
CPDR-L	0.033	0.951	0.921	CPDR: Towards Highly-Efficient Salient Object Detection via Crossed Post-decoder Refinement
TRACER-(ResNet50)	0.033	-	-	TRACER: Extreme Attention Guided Salient Object Tracing Network
CFDN	0.033	-	-	Saliency Detection via Global Context Enhanced Feature Fusion and Edge Weighted Loss
InSPyReNet	0.031	-	-	Revisiting Image Pyramid Structure for High Resolution Salient Object Detection
C4Net	0.029	0.957	0.939	C$^{4}$Net: Contextual Compression and Complementary Combination Network for Salient Object Detection
M3Net-R	0.029	-	-	M$^3$Net: Multilevel, Mixed and Multistage Attention Network for Salient Object Detection
TRACER-TE7	0.026	-	0.940	TRACER: Extreme Attention Guided Salient Object Tracing Network
M3Net-S	0.021	-	-	M$^3$Net: Multilevel, Mixed and Multistage Attention Network for Salient Object Detection

0 of 14 row(s) selected.

Salient Object Detection On Ecssd | SOTA | HyperAI超神経