Papers with Code 아카이브
Image Retrieval
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 10
- 평가표
- 56
- 보존된 평가 기록
- 372
Image Retrieval is a fundamental and long-standing computer vision task that involves finding images similar to a given query from a large database. It is often considered a form of fine-grained, instance-level classification. The task is integral to image recognition alongside classification and cross-modal retrieval. By leveraging visual similarity and other criteria, image retrieval enables users to efficiently discover relevant images, making it a crucial tool in applications such as search and recommendation.
Extending CLIP for Category-to-image Retrieval in E-commerce
<span style="color:grey; opacity: 0.6">( Image credit: DELF )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/bgswaroop/deep-hashing
https://github.com/bnu-wangxun/Deep_Metric
Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning
https://github.com/bombdiggity/paper-bag
Deep Learning based Large Scale Visual Recommendation and Search for E-Commerce
https://github.com/brandonhanx/compfashion
RTIC: Residual Learning for Text and Image Composition using Graph Convolutional Network
https://github.com/bryanplummer/flickr30k_entities
Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models
https://github.com/budnikm/asymmetric_metric_learning
https://github.com/buyeah1109/KEN
https://github.com/buyeah1109/finc
https://github.com/camenduru/llava-colab
https://github.com/capricornguang/a3r
Self-Enhancement Improves Text-Image Retrieval in Foundation Visual-Language Models
https://github.com/cdluminate/advrank-pub
https://github.com/cdluminate/cdluminate
https://github.com/chenggongliang/arcface
VGGFace2: A dataset for recognising faces across pose and age
https://github.com/chengricky/PanoramicScenePlaceRecognition
NetVLAD: CNN architecture for weakly supervised place recognition
https://github.com/chjort/diffusion
Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processing
https://github.com/clemsgrs/hipt
https://github.com/code-implementation1/Code1/tree/main/delf
Detect-to-Retrieve: Efficient Regional Aggregation for Image Search
https://github.com/computationalpathologygroup/hvit
https://github.com/computer-vision-in-the-wild/cvinw_readings
https://github.com/csdongxian/csdongxian
https://github.com/cshizhe/hgr_v2t
VSE++: Improving Visual-Semantic Embeddings with Hard Negatives
https://github.com/csiro-robotics/Pair-VPR
Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval
https://github.com/cvankir2/nsf_auburn
Drone Path-Following in GPS-Denied Environments using Convolutional Networks
https://github.com/cvtower/seesawfacenet_pytorch
VGGFace2: A dataset for recognising faces across pose and age
https://github.com/cydonia999/VGGFace2-pytorch
VGGFace2: A dataset for recognising faces across pose and age
https://github.com/daizuozhuo/batch-dropblock-network
Batch DropBlock Network for Person Re-identification and Beyond
https://github.com/daizuozhuo/batch-feature-erasing-network
Batch DropBlock Network for Person Re-identification and Beyond
https://github.com/deepinsight/insightface
VGGFace2: A dataset for recognising faces across pose and age
https://github.com/dineshreddy91/WALT
https://github.com/dinhvietcuong1996/icme25-inova
https://github.com/dlvuldet/primevul
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
https://github.com/dongkyuk/DOLG-pytorch
DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features
https://github.com/dooleys/fr-nas
VGGFace2: A dataset for recognising faces across pose and age
https://github.com/ducha-aiki/imc2021-sample-kornia-submission
Repeatability Is Not Enough: Learning Affine Regions via Discriminability
https://github.com/ducha-aiki/manifold-diffusion
Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.