← Semi-Supervised Semantic Segmentation

Papers with Code · CC BY-SA 4.0

Cityscapes 6.25% labeled

아카이브 평가 18건 · 마지막 적재/변경 2026-10-30

원본 데이터셋 링크 1

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
모델	원본 지표·값	논문	구현
UniMatch V2 (DINOv2-B)	Validation mIoU 83.6	UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation 2024-10-14	코드 1
SemiVL (ViT-B/16)	Validation mIoU 77.9	SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance 2023-11-27	코드 1
PrevMatch (ResNet-101)	Validation mIoU 77.7%	Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation 2024-05-31	코드 1
CorrMatch (Deeplabv3+ with ResNet-101)	Validation mIoU 77.3	CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation 2023-06-07	코드 1
FARCLUSS	Validation mIoU 77.2	FARCLUSS: Fuzzy Adaptive Rebalancing and Contrastive Uncertainty Learning for Semi-Supervised Semantic Segmentation 2025-06-11	코드 1
S4MC	Validation mIoU 77.00	Semi-Supervised Semantic Segmentation via Marginal Contextual Information 2023-08-26	코드 1
Dual Teacher (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)	Validation mIoU 76.81	Switching Temporary Teachers for Semi-Supervised Semantic Segmentation 2023-09-21	코드 1
UniMatch (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)	Validation mIoU 76.59	Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation 2022-08-21	코드 1
n-CPS (ResNet-50)	Validation mIoU 76.08	n-CPS: Generalising Cross Pseudo Supervision to n Networks for Semi-Supervised Semantic Segmentation 2021-12-14	연결 없음
AEL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)	Validation mIoU 75.83%	Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning 2021-10-11	코드 1
PrevMatch (ResNet-50)	Validation mIoU 75.8%	Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation 2024-05-31	코드 1
CW-BASS (DeepLab v3+ with ResNet-50)	Validation mIoU 75.00	Confidence-Weighted Boundary-Aware Learning for Semi-Supervised Semantic Segmentation 2025-02-21	코드 1
U2PL (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K, AEL)	Validation mIoU 74.90%	Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels 2022-03-08	코드 1
PCR (DeepLab v3+ with ResNet-101 pretraind on ImageNet-1K)	Validation mIoU 73.41%	Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularization 2022-10-10	코드 1
Dense FixMatch (DeepLabv3+ ResNet-101, over-sampling, single pass eval)	Validation mIoU 71.1%	Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks 2022-10-18	코드 1
Dense FixMatch (DeepLabv3+ ResNet-50, uniform sampling, single pass eval)	Validation mIoU 70.65%	Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks 2022-10-18	코드 1
CPCL (DeepLab v3+ with ResNet-50)	Validation mIoU 69.92%	Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation 2022-11-30	코드 1
CPS (DeepLab v3+ with ResNet-101)	Validation mIoU 69.8	Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision 2021-06-02	코드 1 · 코드 2 · 코드 3