Image Retrieval
Image retrieval is a fundamental and enduring computer vision task aimed at finding images similar to a given query image from a large database. This task is often regarded as a form of fine-grained, instance-level classification, where image retrieval can efficiently discover relevant images by leveraging visual similarity and other criteria, playing a crucial role in applications such as search and recommendation.
24/7 Tokyo
HED-N-GAN
AIC-ICC
ERNIE-ViL2.0
AmsterTime
DINOv2 distilled (ViT-L/14 frozen)
CARS196
CGD (MG/SG)
CBVS
UniCLP
CIFAR-10
Custom: 3 conv + 2 fcn
CIRR
SPN4CIR
MS COCO
BLIP-2 ViT-G (fine-tuned)
COCO-CN
COFAR
KRAMT
ConQA Conceptual
CLIP
ConQA Descriptive
CREPE (Compositional REPresentation Evaluation)
ViT-L-14 (LAION400M)
CUB-200-2011
CGD (MG/SG)
DeepFashion
RCCapsNet
DeepFashion - Consumer-to-shop
CTL Model (ResNet50-IBN-A, 320x320)
DeepPatent
SwinV2
Exact Street2Shop
CTL Model (ResNet50-IBN-A, 320x320)
Fashion IQ
FETA Car-Manuals
Flickr30k
BLIP-2 ViT-L (zero-shot, 1K test set)
Flickr30K 1K test
X-VLM (base)
Flickr30k-CN
FooDI-ML (Global)
ADAPT-I2T
FooDI-ML (Spain)
Google Landmarks Dataset v2 (retrieval, validation)
UNICOM-ViT-L-14-512px
Google Landmarks Dataset v2 (retrieval, testing)
AMES
ICFG-PEDES
SSAN
ImageCoDe
ContextualCLIP
In-Shop
CGD (SG/GS)
iNaturalist
Smooth-AP
INRIA Holidays
MultiGrain R50 @ 800
INSTRE
LaSCo
CASE
Localized Narratives
OPT
MSCOCO
HADA
MUGE Retrieval
NUS-WIDE
DTQ
Oxf105k
Oxf5k
Oxford5k
GNN-Reranking
Par106k
Par6k
Offline Diffusion
Paris6k
IME layer
PhotoChat
PKU-Reid
IHDA
PKU SketchRe-ID Dataset
IHDA
ROxford (Hard)
SuperGlobal
ROxford (Medium)
ROxford Medium without fine-tuning
HesAff–rSIFT–VLAD
RParis (Hard)
SuperGlobal
RParis (Medium)
RUC-CAS-WenLan
CMCL
SOP
Unicom+ViT-L@336px
street2shop - topwear
Ranknet
WIT
WIT-ALL