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/eify/clip_benchmark
NLLB-CLIP -- train performant multilingual image retrieval model on a budget
https://github.com/empty16/hardnet.pytorch
Working hard to know your neighbor's margins: Local descriptor learning loss
https://github.com/emrgnt-cmplxty/zero-shot-replication
https://github.com/eric-ai-lab/mitigate-gender-bias-in-image-search
Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search
https://github.com/eric-erki/insightface
VGGFace2: A dataset for recognising faces across pose and age
https://github.com/eternityyw/tram-benchmark
https://github.com/ethz-privsec/superhuman-ai-consistency
https://github.com/ethz-spylab/superhuman-ai-consistency
https://github.com/euwern/proxynca_pp
ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis
https://github.com/evelinehong/VLGrammar
VLGrammar: Grounded Grammar Induction of Vision and Language
https://github.com/fabio-sim/Depth-Anything-ONNX
https://github.com/facebookresearch/MUSE
Improving zero-shot learning by mitigating the hubness problem
https://github.com/facebookresearch/highrescanopyheight
https://github.com/facebookresearch/multimodal
https://github.com/facebookresearch/videoalignment
Particular object retrieval with integral max-pooling of CNN activations
https://github.com/facebookresearch/vissl
https://github.com/fanchenyou/deepdiary
DeepDiary: Automatic Caption Generation for Lifelogging Image Streams
https://github.com/fcakir/deep-mihash
https://github.com/fcakir/hbmp
https://github.com/feymanpriv/DOLG-paddle
DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features
https://github.com/feymanpriv/delg
https://github.com/filipradenovic/cnnimageretrieval
CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples
https://github.com/flyingsheepbin/pet-biometrics
Combination of Multiple Global Descriptors for Image Retrieval
https://github.com/fmaglia/LSH_kNN_graph
An Efficient Approximate kNN Graph Method for Diffusion on Image Retrieval
https://github.com/fongyk/graph-attention
End-to-end Learning of Deep Visual Representations for Image Retrieval
https://github.com/fongyk/graph-simple
End-to-end Learning of Deep Visual Representations for Image Retrieval
https://github.com/forderation/breast-cancer-retrieval
https://github.com/fuqianya/ViLBERT-Paddle
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
https://github.com/fvmassoli/mafer-multires-facial-expression-recognition
VGGFace2: A dataset for recognising faces across pose and age
https://github.com/gchb2012/VQA
Let's Transfer Transformations of Shared Semantic Representations
https://github.com/gjacopo/poppysite
PlaNet - Photo Geolocation with Convolutional Neural Networks
https://github.com/glamor-usc/climb
ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision
https://github.com/gmberton/VPR-methods-evaluation
EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition
https://github.com/gmberton/geo_warp
NetVLAD: CNN architecture for weakly supervised place recognition
https://github.com/google/tirg
Composing Text and Image for Image Retrieval - An Empirical Odyssey
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.