Semi-Supervised Semantic Segmentation 벤치마크

Semi-Supervised Semantic Segmentation on ScribbleKITTI

18개 결과 · ⬇ CSV · JSON

mIoU (1% Labels)

Rank	Model	mIoU (1% Labels)	mIoU (10% Labels)	mIoU (20% Labels)	mIoU (50% Labels)	Paper	Code	Year
1	LaserMix (Voxel)	44.2	53.7	55.1	56.8	LaserMix for Semi-Supervised LiDAR Semantic Segmentation	ldkong1205/LaserMix · yuan-zm/dgt-st	2022
2	MeanTeacher (Voxel)	41.0	50.1	52.8	53.9	Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results	CuriousAI/mean-teacher · ZHKKKe/PixelSSL · benathi/fastswa-semi-sup · +5	2017
3	Sup.-only (Voxel)	39.2	48.0	52.1	53.8	Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation	xinge008/Cylinder3D · L-Reichardt/Cylinder3D-updated-CUDA	2020
4	LaserMix (Range View)	38.3	54.4	55.6	58.7	LaserMix for Semi-Supervised LiDAR Semantic Segmentation	ldkong1205/LaserMix · yuan-zm/dgt-st	2022
5	CutMix-Seg (Range View)	36.7	50.7	52.9	54.3	Semi-supervised semantic segmentation needs strong, varied perturbations	ZHKKKe/PixelSSL · lorenmt/reco · Britefury/cutmix-semisup-seg · +2	2019
6	CBST (Range View)	35.7	50.7	52.7	54.6	Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training	yzou2/CBST	2018
7	MeanTeacher (Range View)	34.2	49.8	51.6	53.3	Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results	CuriousAI/mean-teacher · ZHKKKe/PixelSSL · benathi/fastswa-semi-sup · +5	2017
8	CPS (Range View)	33.7	50.0	52.8	54.6	Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision	charlesCXK/TorchSemiSeg · harshm121/m3l · yhuang1997/3D-CPS	2021
9	Sup.-only (Range View)	33.1	47.7	49.9	52.5	FIDNet: LiDAR Point Cloud Semantic Segmentation with Fully Interpolation Decoding	placeforyiming/iros21-fidnet-semantickitti	2021
10	LaserMix (Voxel)	44.2	53.7	55.1	56.8	LaserMix for Semi-Supervised LiDAR Semantic Segmentation	ldkong1205/LaserMix · yuan-zm/dgt-st	2022
11	MeanTeacher (Voxel)	41.0	50.1	52.8	53.9	Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results	CuriousAI/mean-teacher · ZHKKKe/PixelSSL · benathi/fastswa-semi-sup · +5	2017
12	Sup.-only (Voxel)	39.2	48.0	52.1	53.8	Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation	xinge008/Cylinder3D · L-Reichardt/Cylinder3D-updated-CUDA	2020
13	LaserMix (Range View)	38.3	54.4	55.6	58.7	LaserMix for Semi-Supervised LiDAR Semantic Segmentation	ldkong1205/LaserMix · yuan-zm/dgt-st	2022
14	CutMix-Seg (Range View)	36.7	50.7	52.9	54.3	Semi-supervised semantic segmentation needs strong, varied perturbations	ZHKKKe/PixelSSL · lorenmt/reco · Britefury/cutmix-semisup-seg · +2	2019
15	CBST (Range View)	35.7	50.7	52.7	54.6	Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training	yzou2/CBST	2018
16	MeanTeacher (Range View)	34.2	49.8	51.6	53.3	Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results	CuriousAI/mean-teacher · ZHKKKe/PixelSSL · benathi/fastswa-semi-sup · +5	2017
17	CPS (Range View)	33.7	50.0	52.8	54.6	Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision	charlesCXK/TorchSemiSeg · harshm121/m3l · yhuang1997/3D-CPS	2021
18	Sup.-only (Range View)	33.1	47.7	49.9	52.5	FIDNet: LiDAR Point Cloud Semantic Segmentation with Fully Interpolation Decoding	placeforyiming/iros21-fidnet-semantickitti	2021