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/PaddlePaddle/PaddleClas/blob/develop/docs/zh_CN/training/metric_learning/xbm.md
https://github.com/PuchatekwSzortach/combination_of_multiple_global_descriptors_for_image_retrieval
Combination of Multiple Global Descriptors for Image Retrieval
https://github.com/Qidian213/Ranked_Person_ReID
https://github.com/QuocThangNguyen/deep-metric-learning-tsinghua-dogs
SoftTriple Loss: Deep Metric Learning Without Triplet Sampling
https://github.com/Raykoooo/3rd_place_to_Kaggle_Google_Landmark_Retrieval_2020
https://github.com/Recognito-Vision/Android-FaceRecognition-FaceLivenessDetection
https://github.com/Recognito-Vision/Face-SDK-Linux-Demos
https://github.com/Recognito-Vision/Linux-FaceRecognition-FaceLivenessDetection
VGGFace2: A dataset for recognising faces across pose and age
https://github.com/ReemHal/Browser-Based-Annotator
https://github.com/RocketFlash/easy_metric_learning/tree/master/tools
Unicom: Universal and Compact Representation Learning for Image Retrieval
https://github.com/RuibinMa/comp755project-ruibinma
CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples
https://github.com/Samjoel3101/Self-Supervised-Learning-fastai2
Combination of Multiple Global Descriptors for Image Retrieval
https://github.com/SforAiDl/CountCLIP
https://github.com/Shiro-LK/python-DOLG
Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval
https://github.com/ShivaKrishnaM/ZS-SBIR
https://github.com/SilverIonn/EPHN-OpenSet
https://github.com/Sorananakiii/Fine-grained-image-recognition
https://github.com/THUDM/CogAgent
https://github.com/TRAILab/ST-SLidR
https://github.com/TencentYoutuResearch/BaseArchitecture-EAT
Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model
https://github.com/ThanThoai/Visual-Question-Answering_Vietnamese
Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks
https://github.com/TheChalice/Annotator
https://github.com/TinyZeaMays/CircleLoss
Circle Loss: A Unified Perspective of Pair Similarity Optimization
https://github.com/TreB1eN/InsightFace_Pytorch
VGGFace2: A dataset for recognising faces across pose and age
https://github.com/Tsingularity/FRN
DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning
https://github.com/VadymV/ICOS
Are we done with object recognition? The iCub robot's perspective
https://github.com/VectorSpaceLab/MegaPairs
MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval
https://github.com/Vigneshthanga/stackGAN-v2
Learning Deep Representations of Fine-grained Visual Descriptions
https://github.com/Vijetha1/WDHT
https://github.com/Vill-Lab/2023-TIFS-DTIBA
FastReID: A Pytorch Toolbox for General Instance Re-identification
https://github.com/VinitSR7/Image-Caption-Generation
Deep Visual-Semantic Alignments for Generating Image Descriptions
https://github.com/Vishal-V/StackGAN
Learning Deep Representations of Fine-grained Visual Descriptions
https://github.com/WebQnA/WebQA_Baseline
https://github.com/WeidiXie/Keras-VGGFace2-ResNet50
VGGFace2: A dataset for recognising faces across pose and age
https://github.com/X-PLUG/mPLUG-2
mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.