← Semi-Supervised Semantic Segmentation
Papers with Code · CC BY-SA 4.0

nuScenes

아카이브 평가 11건 · 마지막 적재/변경

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델원본 지표·값논문구현
PLE (Voxel)
mIoU (1% Labels)
62.9
mIoU (10% Labels)
74.3
mIoU (20% Labels)
76
mIoU (50% Labels)
76.1
mIoU (0.5% Labels)
58
mIoU (2% Labels)
67.2
mIoU (5% Labels)
72.8
Learning from Spatio-temporal Correlation for Semi-Supervised LiDAR Semantic Segmentation
2024-10-09
코드 1
LaserMix (Voxel)
mIoU (0.5% Labels)
51.4
mIoU (2% Labels)
63.9
mIoU (5% Labels)
69.7
Learning from Spatio-temporal Correlation for Semi-Supervised LiDAR Semantic Segmentation
2024-10-09
코드 1
LaserMix (Voxel)
mIoU (1% Labels)
55.3
mIoU (10% Labels)
69.9
mIoU (20% Labels)
71.8
mIoU (50% Labels)
73.2
LaserMix for Semi-Supervised LiDAR Semantic Segmentation
2022-06-30
코드 1 · 코드 2
MeanTeacher (Voxel)
mIoU (1% Labels)
51.6
mIoU (10% Labels)
66.0
mIoU (20% Labels)
67.1
mIoU (50% Labels)
71.7
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
2017-03-06
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8
Sup.-only (Voxel)
mIoU (1% Labels)
50.9
mIoU (10% Labels)
65.9
mIoU (20% Labels)
66.6
mIoU (50% Labels)
71.2
Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation
2020-11-19
코드 1 · 코드 2
LaserMix (Range View)
mIoU (1% Labels)
49.5
mIoU (10% Labels)
68.2
mIoU (20% Labels)
70.6
mIoU (50% Labels)
73.0
LaserMix for Semi-Supervised LiDAR Semantic Segmentation
2022-06-30
코드 1 · 코드 2
CutMix-Seg (Range View)
mIoU (1% Labels)
43.8
mIoU (10% Labels)
63.9
mIoU (20% Labels)
64.8
mIoU (50% Labels)
69.8
Semi-supervised semantic segmentation needs strong, varied perturbations
2019-06-05
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
MeanTeacher (Range View)
mIoU (1% Labels)
42.1
mIoU (10% Labels)
60.4
mIoU (20% Labels)
65.4
mIoU (50% Labels)
69.4
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
2017-03-06
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6 · 코드 7 · 코드 8
CBST (Range View)
mIoU (1% Labels)
40.9
mIoU (10% Labels)
60.5
mIoU (20% Labels)
64.3
mIoU (50% Labels)
69.3
Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training
2018-09-01
코드 1
CPS (Range View)
mIoU (1% Labels)
40.7
mIoU (10% Labels)
60.8
mIoU (20% Labels)
64.9
mIoU (50% Labels)
68.0
Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
2021-06-02
코드 1 · 코드 2 · 코드 3
Sup.-only (Range View)
mIoU (1% Labels)
38.3
mIoU (10% Labels)
57.5
mIoU (20% Labels)
62.7
mIoU (50% Labels)
67.6
FIDNet: LiDAR Point Cloud Semantic Segmentation with Fully Interpolation Decoding
2021-09-08
코드 1