Papers with Code 아카이브
Described Object Detection
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 8
Described Object Detection (DOD) detects all instances on each image in the dataset, based on a flexible reference. It is a superset of Open-Vocabulary Object Detection (OVD) and Referring Expression Comprehension (REC). It expands category names to flexible language expressions for OVD and overcomes the limitation of REC only grounding the pre-existing object. Works related to DOD are tracked in awesome-DOD list on github.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models
Described Object Detection: Liberating Object Detection with Flexible Expressions
CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching
Universal Instance Perception as Object Discovery and Retrieval
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone
Simple Open-Vocabulary Object Detection with Vision Transformers
Grounded Language-Image Pre-training
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.