Papers with Code · CC BY-SA 4.0

DAVIS 2016

아카이브 평가 24건 · 마지막 적재/변경 2026-10-30

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
ISVOS (BL30K, MS)	Jaccard (Mean) 92.5 F-Score 94.2 J&F 93.4	Look Before You Match: Instance Understanding Matters in Video Object Segmentation 2022-12-13	연결 없음
XMem (BL30K, MS)	Jaccard (Mean) 92.2 F-Score 94.4 J&F 93.3	XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model 2022-07-14	코드 1 · 코드 2
BATMAN (val)	Jaccard (Mean) 90.7 F-Score 94.2 J&F 92.5	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation 2022-08-01	연결 없음
STCN (val)	Jaccard (Mean) 90.8 F-Score 92.5 J&F 91.6	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation 2022-08-01	연결 없음
XMem	Jaccard (Mean) 90.4 F-Score 92.7 J&F 91.5	XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model 2022-07-14	코드 1 · 코드 2
MobileVOS (val)	Jaccard (Mean) 90.3 F-Score 92.6 J&F 91.4	MobileVOS: Real-Time Video Object Segmentation Contrastive Learning meets Knowledge Distillation 2023-03-14	연결 없음
AOT (val)	Jaccard (Mean) 90.1 F-Score 92.1 J&F 91.1	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation 2022-08-01	연결 없음
LCM (val)	Jaccard (Mean) 89.9 F-Score 91.4 J&F 90.7	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation 2022-08-01	연결 없음
RPCMVOS (val)	Jaccard (Mean) 87.1 F-Score 94 J&F 90.6	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation 2022-08-01	연결 없음
KMN (val)	Jaccard (Mean) 89.5 F-Score 91.5 J&F 90.5	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation 2022-08-01	연결 없음
TransVOS (val)	Jaccard (Mean) 89.8 F-Score 91.2 J&F 90.5	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation 2022-08-01	연결 없음
CFBI+ (val)	Jaccard (Mean) 88.7 F-Score 91.1 J&F 89.9	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation 2022-08-01	연결 없음
ViTAE-T-Stage	Jaccard (Mean) 89.2 F-Score 90.4 J&F 89.8	ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias 2021-06-07	코드 1 · 코드 2
CFBI (val)	Jaccard (Mean) 88.3 F-Score 90.5 J&F 89.4	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation 2022-08-01	연결 없음
RMN (val)	Jaccard (Mean) 88.9 F-Score 88.7 J&F 88.8	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation 2022-08-01	연결 없음
AOC-MF (val)	Jaccard (Mean) 88.5 F-Score 94.7	Towards Robust Video Object Segmentation with Adaptive Object Calibration 2022-07-02	코드 1
STM (val)	Jaccard (Mean) 88.7 F-Score 89.9	BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation 2022-08-01	연결 없음
3DC-Seg	Jaccard (Mean) 84.3 F-Score 84.7	Making a Case for 3D Convolutions for Object Segmentation in Videos 2020-08-26	코드 1
DFNet	F-Score 81.8	Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation 2020-08-04	연결 없음
Ours	Jaccard (Mean) 83.4	Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation 2020-08-04	연결 없음
VOSwL (Mask+Language)	mIoU 84.5	Video Object Segmentation with Language Referring Expressions 2018-03-21	연결 없음
VOSwL (Language)	mIoU 82.8	Video Object Segmentation with Language Referring Expressions 2018-03-21	연결 없음
LOCATE	mIoU 80.9 Contour Accuracy 88.7	LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training 2023-08-22	코드 1
FODVid	mIoU 78.71	FODVid: Flow-guided Object Discovery in Videos 2023-07-10	연결 없음