Scene Text Detection On Total Text

评估指标

F-Measure

FPS

Precision

Recall

评测结果

各个模型在此基准测试上的表现结果

					Paper Title	Repository
MixNet	90.5%	15.2	93.0	88.1	MixNet: Toward Accurate Detection of Challenging Scene Text in the Wild
SRFormer (ResNet-50)	90.0%	-	92.2%	87.9%	SRFormer: Text Detection Transformer with Incorporated Segmentation and Regression
DPText-DETR (ResNet-50)	89.0%	17	91.8%	86.4%	DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer
TextFuseNet (ResNeXt-101)	87.5%	-	89.2	85.8	TextFuseNet: Scene Text Detection with Richer Fused Features	-
FAST-B-800	87.5%	46	90.0	85.2	FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation
I3CL + SSL(ResNet-50)	86.9%	-	89.8	84.2	I3CL:Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection
CharNet H-88 (multi-scale)	86.5%	-	88	85	Convolutional Character Networks
FAST-B-640	86.4%	67.5	89.9	83.2	FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation
DBNet++ (ResNet-50) (800)	86%	28	88.9	83.2	Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion
FAST-B-512	85.8%	93.2	89.6	82.4	FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation
CharNet H-88	85.6%	-	89.9	81.7	Convolutional Character Networks
SA-Text	85.6%	-	-	-	A method for detecting text of arbitrary shapes in natural scenes that improves text spotting	-
PAN-640	85%	-	89.3	81	Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network
FAST-S-512	84.9%	115.5	88.3	81.7	FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation
DB-ResNet-50 (800)	84.7%	-	-	-	Real-time Scene Text Detection with Differentiable Binarization
TextCohesion	84.6%	-	-	-	TextCohesion: Detecting Text for Arbitrary Shapes	-
CRAFT	83.6%	-	87.6	79.9	Character Region Awareness for Text Detection
DBNet++ (ResNet-18) (800)	83.3%	48	87.4	79.6	Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion
SPCNET	82.9%	-	83	82.8	Scene Text Detection with Supervised Pyramid Context Network
FAST-T-448	81.6%	152.8	86.5	77.2	FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation

0 of 27 row(s) selected.