Startseite Neuigkeiten Neueste Forschungsarbeiten Tutorials Datensätze Wiki SOTA LLM-Modelle GPU-Rangliste Veranstaltungen

Deutsch

Salient Object Detection On Hku Is

Metriken

MAE

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	MAE	Paper Title	Repository
TRACER-(ResNet50)	0.028	TRACER: Extreme Attention Guided Salient Object Tracing Network
CPD-R (ResNet50)	0.034	Cascaded Partial Decoder for Fast and Accurate Salient Object Detection
TRACER-TE7	0.020	TRACER: Extreme Attention Guided Salient Object Tracing Network
M3Net-S	0.019	M$^3$Net: Multilevel, Mixed and Multistage Attention Network for Salient Object Detection
UCNet-CVAE	0.026	Uncertainty Inspired RGB-D Saliency Detection
PoolNet (VGG-16)	0.03	A Simple Pooling-Based Design for Real-Time Salient Object Detection
C4Net	0.025	C$^{4}$Net: Contextual Compression and Complementary Combination Network for Salient Object Detection	-
DSS (Res2Net-50)	0.05	Res2Net: A New Multi-scale Backbone Architecture
BASNet	0.032	BASNet: Boundary-Aware Salient Object Detection	-
UCNet-ABP	0.027	Uncertainty Inspired RGB-D Saliency Detection
InSPyReNet	0.028	Revisiting Image Pyramid Structure for High Resolution Salient Object Detection
CPDR-L	0.028	CPDR: Towards Highly-Efficient Salient Object Detection via Crossed Post-decoder Refinement	-
M3Net-R	0.026	M$^3$Net: Multilevel, Mixed and Multistage Attention Network for Salient Object Detection
HybridSOD	0.038	A Weakly Supervised Learning Framework for Salient Object Detection via Hybrid Labels

0 of 14 row(s) selected.