https://github.com/MasterBin-IIAU/UNINEXT
공식 코드Universal Instance Perception as Object Discovery and Retrieval
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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/alpha-vllm/llama2-accessory
공식 코드https://github.com/google-research/scenic/tree/main/scenic/projects/owl_vit
공식 코드Simple Open-Vocabulary Object Detection with Vision Transformers
https://github.com/microsoft/GLIP
공식 코드https://github.com/microsoft/fiber
공식 코드Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone
https://github.com/open-mmlab/mmdetection
공식 코드An Open and Comprehensive Pipeline for Unified Object Grounding and Detection
https://github.com/shikras/d-cube
공식 코드Described Object Detection: Liberating Object Detection with Flexible Expressions
https://github.com/tgxs002/cora
공식 코드CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching
https://github.com/brown-palm/ObjectPrompt
https://github.com/cszzshi/SimD
An Open and Comprehensive Pipeline for Unified Object Grounding and Detection
https://github.com/rsCPSyEu/ovd_cod
https://github.com/yangyucheng000/University/tree/main/model-1/owlvit
Simple Open-Vocabulary Object Detection with Vision Transformers
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.