← Video Instance Segmentation
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.
| 모델 | 원본 지표·값 | 논문 | 구현 |
|---|---|---|---|
| CAVIS(VIT-L, Offline) |
|
Context-Aware Video Instance Segmentation 2024-07-03 |
코드 1 |
| DVIS-DAQ(VIT-L, Offline) |
|
DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries 2024-03-29 |
코드 1 · 코드 2 · 코드 3 |
| DVIS++(VIT-L, Offline) |
|
DVIS++: Improved Decoupled Framework for Universal Video Segmentation 2023-12-20 |
코드 1 |
| DVIS++(VIT-L, Online) |
|
DVIS++: Improved Decoupled Framework for Universal Video Segmentation 2023-12-20 |
코드 1 |
| RefineVIS (Swin-L, online) |
|
RefineVIS: Video Instance Segmentation with Temporal Attention Refinement 2023-06-07 |
연결 없음 |
| GRAtt-VIS (Swin-L) |
|
GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance Segmentation 2023-05-26 |
코드 1 |
| TarViS (Swin-L) |
|
TarViS: A Unified Approach for Target-based Video Segmentation 2023-01-06 |
코드 1 |
| DVIS(Swin-L) |
|
DVIS: Decoupled Video Instance Segmentation Framework 2023-06-06 |
코드 1 |
| GenVIS (Swin-L) |
|
A Generalized Framework for Video Instance Segmentation 2022-11-16 |
코드 1 |
| NOVIS (Swin-L) |
|
NOVIS: A Case for End-to-End Near-Online Video Instance Segmentation 2023-08-29 |
연결 없음 |
| Tube-Link(Swin-L) |
|
Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation 2023-03-22 |
코드 1 |
| UniVS(Swin-L) |
|
UniVS: Unified and Universal Video Segmentation with Prompts as Queries 2024-02-28 |
코드 1 |
| VITA (Swin-L) |
|
VITA: Video Instance Segmentation via Object Token Association 2022-06-09 |
코드 1 |
| IDOL (Swin-L) |
|
In Defense of Online Models for Video Instance Segmentation 2022-07-21 |
코드 1 · 코드 2 |
| MDQE(Swin-L) |
|
MDQE: Mining Discriminative Query Embeddings to Segment Occluded Instances on Challenging Videos 2023-03-25 |
코드 1 |
| MinVIS (Swin-L) |
|
MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training 2022-08-03 |
코드 1 · 코드 2 |
| DeVIS (Swin-L) |
|
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation 2022-07-22 |
코드 1 |
| BoxVIS(Swin-L & Box-sup) |
|
BoxVIS: Video Instance Segmentation with Box Annotations 2023-03-26 |
코드 1 |
| InstanceFormer (Swin-L) |
|
InstanceFormer: An Online Video Instance Segmentation Framework 2022-08-22 |
코드 1 |
| TarViS (Swin-T) |
|
TarViS: A Unified Approach for Target-based Video Segmentation 2023-01-06 |
코드 1 |
| GRAtt-VIS (ResNet-50) |
|
GRAtt-VIS: Gated Residual Attention for Auto Rectifying Video Instance Segmentation 2023-05-26 |
코드 1 |
| TarViS (ResNet-50) |
|
TarViS: A Unified Approach for Target-based Video Segmentation 2023-01-06 |
코드 1 |
| NOVIS (ResNet-50) |
|
NOVIS: A Case for End-to-End Near-Online Video Instance Segmentation 2023-08-29 |
연결 없음 |
| DeVIS (ResNet-50) |
|
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation 2022-07-22 |
코드 1 |
| InstanceFormer (ResNet-50) |
|
InstanceFormer: An Online Video Instance Segmentation Framework 2022-08-22 |
코드 1 |
| STMask(R101-DCN-FPN) |
|
Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation 2021-04-06 |
코드 1 |