Papers with Code · CC BY-SA 4.0

YouTube-VIS validation

아카이브 평가 43건 · 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
CAVIS(ViT-L, Online)	mask AP 68.9 AP50 89.3 AP75 76.2 AR1 58.3 AR10 73.6	Context-Aware Video Instance Segmentation 2024-07-03	코드 1
DVIS++(ViT-L, Online)	mask AP 67.7 AP50 88.8 AP75 75.3 AR1 57.9 AR10 73.7	DVIS++: Improved Decoupled Framework for Universal Video Segmentation 2023-12-20	코드 1
DVIS	mask AP 64.9 AP50 88.0 AP75 72.7 AR1 56.5 AR10 70.3	DVIS: Decoupled Video Instance Segmentation Framework 2023-06-06	코드 1
Tube-Link	mask AP 64.6 AP50 86.6 AP75 71.3 AR1 55.9 AR10 69.1	Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation 2023-03-22	코드 1
MinVIS (Swin-L)	mask AP 61.6 AP50 83.3 AP75 68.6 AR1 54.8 AR10 66.6	MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training 2022-08-03	코드 1 · 코드 2
Mask2Former (Swin-L)	mask AP 60.4 AP50 84.4 AP75 67.0	Mask2Former for Video Instance Segmentation 2021-12-20	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6
UniVS(Swin-L)	mask AP 60.0 AP50 82.1 AP75 65.3 AR1 54.7 AR10 66.8	UniVS: Unified and Universal Video Segmentation with Prompts as Queries 2024-02-28	코드 1
MDQE(Swin-L)	mask AP 59.9 AP50 84.9 AP75 67.3 AR1 53.5 AR10 65.0	MDQE: Mining Discriminative Query Embeddings to Segment Occluded Instances on Challenging Videos 2023-03-25	코드 1
SeqFormer (Swin-L)	mask AP 59.3 AP50 82.1 AP75 66.4 AR1 51.7 AR10 64.4	SeqFormer: Sequential Transformer for Video Instance Segmentation 2021-12-15	코드 1 · 코드 2
DeVIS (Swin-L)	mask AP 57.1 AP50 80.8 AP75 66.3 AR1 50.8 AR10 61.0	DeVIS: Making Deformable Transformers Work for Video Instance Segmentation 2022-07-22	코드 1
InstanceFormer(Swin-L)	mask AP 56.3 AP50 78.0 AP75 64.2 AR1 50.9 AR10 61.6	InstanceFormer: An Online Video Instance Segmentation Framework 2022-08-22	코드 1
TCIS (Swin-S)	mask AP 54.3 AP50 76.6 AP75 65.6 AR1 47 AR10 57.9	1st Place Solution for YouTubeVOS Challenge 2021:Video Instance Segmentation 2021-06-12	연결 없음
Video K-Net (Swin-Base)	mask AP 54.1 AP50 79.0 AP75 59.6 AR1 49.7 AR10 59.9	Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation 2022-04-10	코드 1
NOVIS (ResNet-50)	mask AP 52.8 AP50 75.7 AP75 56.9 AR1 50.3 AR10 60.6	NOVIS: A Case for End-to-End Near-Online Video Instance Segmentation 2023-08-29	연결 없음
IDOL (ResNet-50)	mask AP 49.5 AP50 74 AP75 52.9 AR1 47.7 AR10 58.7	In Defense of Online Models for Video Instance Segmentation 2022-07-21	코드 1 · 코드 2
Mask2Former (ResNet-101)	mask AP 49.2 AP50 72.8 AP75 54.2	Mask2Former for Video Instance Segmentation 2021-12-20	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6
SeqFormer (ResNet-101)	mask AP 49.0 AP50 71.1 AP75 55.7 AR1 46.8 AR10 56.9	SeqFormer: Sequential Transformer for Video Instance Segmentation 2021-12-15	코드 1 · 코드 2
MSN	mask AP 48.8 AP50 69.4 AP75 54.9 AR1 40.1 AR10 55.0	MSN: Efficient Online Mask Selection Network for Video Instance Segmentation 2021-06-19	코드 1
SeqFormer (ResNet-50)	mask AP 45.1 AP50 66.9 AP75 50.5 AR1 45.6 AR10 54.6	SeqFormer: Sequential Transformer for Video Instance Segmentation 2021-12-15	코드 1 · 코드 2
Mask2Former (ResNet-50)	mask AP 46.4 AP50 68.0 AP75 50.0	Mask2Former for Video Instance Segmentation 2021-12-20	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 · 코드 6
InstanceFormer(ResNet-50)	mask AP 45.6 AP50 68.6 AP75 49.6 AR1 42.1 AR10 53.5	InstanceFormer: An Online Video Instance Segmentation Framework 2022-08-22	코드 1
DeVIS (ResNet-50)	mask AP 44.4 AP50 66.7 AP75 48.6 AR1 42.4 AR10 51.6	DeVIS: Making Deformable Transformers Work for Video Instance Segmentation 2022-07-22	코드 1
IFC (ResNet-50)	mask AP 42.8 AP50 65.8 AP75 46.8 AR1 43.8 AR10 51.2	Video Instance Segmentation using Inter-Frame Communication Transformers 2021-06-07	코드 1
VisTR(ResNet-101)	mask AP 40.1 AP50 64.0 AP75 45.0 AR1 38.3 AR10 44.9	End-to-End Video Instance Segmentation with Transformers 2020-11-30	코드 1 · 코드 2
VSTAM	mask AP 39.0	Video Sparse Transformer With Attention-Guided Memory for Video Object Detection 2022-06-17	코드 1
STMask(R101-DCN-FPN)	mask AP 36.8 AP50 56.8 AP75 38.0 AR1 34.8 AR10 41.8	Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation 2021-04-06	코드 1
STC (ResNet-50)	mask AP 36.7 AP50 57.2 AP75 38.6 AR1 36.9 AR10 44.5	STC: Spatio-Temporal Contrastive Learning for Video Instance Segmentation 2022-02-08	연결 없음
CrossVIS (ResNet-101)	mask AP 36.6 AP50 57.3 AP75 39.7 AR1 36 AR10 42	Crossover Learning for Fast Online Video Instance Segmentation 2021-04-13	코드 1
VisTR(ResNet-50)	mask AP 36.2 AP50 59.8 AP75 36.9 AR1 37.2 AR10 42.4	End-to-End Video Instance Segmentation with Transformers 2020-11-30	코드 1 · 코드 2
PCAN(ResNet-50)	mask AP 36.1 AP50 54.9 AP75 39.4 AR1 36.3 AR10 41.6	Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation 2021-06-22	코드 1