https://github.com/BUAADreamer/SPN4CIR
공식 코드Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives
Papers with Code 아카이브
Composed Image Retrieval (CoIR)
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 2
- 보존된 평가 기록
- 2
Composed Image Retrieval (CoIR) is the task involves retrieving images from a large database based on a query composed of multiple elements, such as text, images, and sketches. The goal is to develop algorithms that can understand and combine multiple sources of information to accurately retrieve images that match the query, extending the user’s expression ability.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/Chen-Junyang-cn/PLI
공식 코드Pretrain like Your Inference: Masked Tuning Improves Zero-Shot Composed Image Retrieval
https://github.com/Code-kunkun/ZS-CIR
공식 코드https://github.com/Cuberick-Orion/Bi-Blip4CIR
공식 코드Bi-directional Training for Composed Image Retrieval via Text Prompt Learning
https://github.com/Cuberick-Orion/CIRPLANT
공식 코드Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models
https://github.com/Cuberick-Orion/CIRR
공식 코드Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models
https://github.com/Cuberick-Orion/Candidate-Reranking-CIR
공식 코드Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder
https://github.com/Monoxide-Chen/uncertainty_retrieval
공식 코드Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization
https://github.com/Pter61/osrcir
공식 코드https://github.com/billpsomas/rscir
공식 코드https://github.com/chunmeifeng/sprc
공식 코드https://github.com/explainableml/vision_by_language
공식 코드Vision-by-Language for Training-Free Compositional Image Retrieval
https://github.com/google-deepmind/magiclens
공식 코드MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions
https://github.com/google-research/composed_image_retrieval
공식 코드Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval
https://github.com/hmchuong/CoLLM
공식 코드https://github.com/levymsn/LaSCo
공식 코드Data Roaming and Quality Assessment for Composed Image Retrieval
https://github.com/lucas-ventura/CoVR
공식 코드CoVR-2: Automatic Data Construction for Composed Video Retrieval
https://github.com/miccunifi/circo
공식 코드https://github.com/miccunifi/searle
공식 코드https://github.com/navervision/compodiff
공식 코드CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion
https://github.com/navervision/lincir
공식 코드Language-only Efficient Training of Zero-shot Composed Image Retrieval
https://github.com/nikosefth/freedom
공식 코드Composed Image Retrieval for Training-Free Domain Conversion
https://github.com/nvlabs/palavra
공식 코드"This is my unicorn, Fluffy": Personalizing frozen vision-language representations
https://github.com/nvlabs/pervlbenchmark
공식 코드"This is my unicorn, Fluffy": Personalizing frozen vision-language representations
https://github.com/pengfei-luo/ImageScope
공식 코드ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning
https://github.com/pter61/context-i2w
공식 코드https://github.com/pter61/predicir
공식 코드https://github.com/suoych/keds
공식 코드Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval
https://github.com/whats2000/WeiMoCIR
공식 코드Training-free Zero-shot Composed Image Retrieval via Weighted Modality Fusion and Similarity
https://github.com/VectorSpaceLab/MegaPairs
MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval
https://github.com/naver/artemis
Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models
https://github.com/yzy-bupt/LDRE
https://github.com/yzy-bupt/SEIZE
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.