Papers with Code 아카이브
Generalized Referring Expression Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 13
Generalized Referring Expression Segmentation (GRES), introduced by Liu et al in CVPR 2023, allows expressions indicating any number of target objects. GRES takes an image and a referring expression as input, and requires mask prediction of the target object(s).
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Refer to Anything with Vision-Language Prompts
Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehension
Instance-Aware Generalized Referring Expression Segmentation
Bring Adaptive Binding Prototypes to Generalized Referring Expression Segmentation
CoHD: A Counting-Aware Hierarchical Decoding Framework for Generalized Referring Expression Segmentation
PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model
GROUNDHOG: Grounding Large Language Models to Holistic Segmentation
GSVA: Generalized Segmentation via Multimodal Large Language Models
GRES: Generalized Referring Expression Segmentation
LAVT: Language-Aware Vision Transformer for Referring Image Segmentation
CRIS: CLIP-Driven Referring Image Segmentation
Vision-Language Transformer and Query Generation for Referring Segmentation
Locate then Segment: A Strong Pipeline for Referring Image Segmentation
MAttNet: Modular Attention Network for Referring Expression Comprehension
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.