الرئيسية الأخبار أحدث الأوراق البحثية الدروس مجموعات البيانات الموسوعة SOTA نماذج LLM لوحة الأداء GPU الفعاليات

العربية

Semi Supervised Semantic Segmentation On 25

المقاييس

mIoU (1% Labels)

mIoU (10% Labels)

mIoU (20% Labels)

mIoU (50% Labels)

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج	mIoU (1% Labels)	mIoU (10% Labels)	mIoU (20% Labels)	mIoU (50% Labels)	Paper Title	Repository
Sup.-only (Range View)	38.3	57.5	62.7	67.6	FIDNet: LiDAR Point Cloud Semantic Segmentation with Fully Interpolation Decoding
MeanTeacher (Range View)	42.1	60.4	65.4	69.4	Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
CPS (Range View)	40.7	60.8	64.9	68.0	Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
PLE (Voxel)	62.9	74.3	76	76.1	Learning from Spatio-temporal Correlation for Semi-Supervised LiDAR Semantic Segmentation
CBST (Range View)	40.9	60.5	64.3	69.3	Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training
Sup.-only (Voxel)	50.9	65.9	66.6	71.2	Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation
LaserMix (Voxel)	-	-	-	-	Learning from Spatio-temporal Correlation for Semi-Supervised LiDAR Semantic Segmentation
CutMix-Seg (Range View)	43.8	63.9	64.8	69.8	Semi-supervised semantic segmentation needs strong, varied perturbations
LaserMix (Range View)	49.5	68.2	70.6	73.0	LaserMix for Semi-Supervised LiDAR Semantic Segmentation
MeanTeacher (Voxel)	51.6	66.0	67.1	71.7	Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
LaserMix (Voxel)	55.3	69.9	71.8	73.2	LaserMix for Semi-Supervised LiDAR Semantic Segmentation

0 of 11 row(s) selected.