SOTAVerified

Image Retrieval

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

( Image credit: DELF )

Papers

Showing 201250 of 2239 papers

TitleStatusHype
Fast and Incremental Loop Closure Detection Using Proximity GraphsCode1
CSIM: A Copula-based similarity index sensitive to local changes for Image quality assessmentCode1
DAS: Densely-Anchored Sampling for Deep Metric LearningCode1
DASGIL: Domain Adaptation for Semantic and Geometric-aware Image-based LocalizationCode1
Feature Representation Learning for Unsupervised Cross-domain Image RetrievalCode1
GSV-Cities: Toward Appropriate Supervised Visual Place RecognitionCode1
Accurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image MatchingCode1
Data Roaming and Quality Assessment for Composed Image RetrievalCode1
Hierarchical Average Precision Training for Pertinent Image RetrievalCode1
Hierarchy-of-Visual-Words: a Learning-based Approach for Trademark Image RetrievalCode1
Hot-Refresh Model Upgrades with Regression-Alleviating Compatible Training in Image RetrievalCode1
HPointLoc: Point-based Indoor Place Recognition using Synthetic RGB-D ImagesCode1
HyP^2 Loss: Beyond Hypersphere Metric Space for Multi-label Image RetrievalCode1
AugNet: End-to-End Unsupervised Visual Representation Learning with Image AugmentationCode1
Unsupervised Sketch-to-Photo SynthesisCode1
Image Generation Diversity Issues and How to Tame ThemCode1
Image Retrieval on Real-life Images with Pre-trained Vision-and-Language ModelsCode1
DeepEMD: Differentiable Earth Mover's Distance for Few-Shot LearningCode1
Chatting Makes Perfect: Chat-based Image RetrievalCode1
IMPACT: A Large-scale Integrated Multimodal Patent Analysis and Creation Dataset for Design PatentsCode1
Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and NegativesCode1
Improving Deep Metric Learning by Divide and ConquerCode1
DenserNet: Weakly Supervised Visual Localization Using Multi-scale Feature AggregationCode1
EDIS: Entity-Driven Image Search over Multimodal Web ContentCode1
DeepPatent: Large scale patent drawing recognition and retrievalCode1
Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play ApproachCode1
ChiQA: A Large Scale Image-based Real-World Question Answering Dataset for Multi-Modal UnderstandingCode1
Analogous to Evolutionary Algorithm: Designing a Unified Sequence ModelCode1
Introspective Deep Metric Learning for Image RetrievalCode1
BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean LabelCode1
Expressive Scene Graph Generation Using Commonsense Knowledge Infusion for Visual Understanding and ReasoningCode1
EViT: Privacy-Preserving Image Retrieval via Encrypted Vision Transformer in Cloud ComputingCode1
It's All About Your Sketch: Democratising Sketch Control in Diffusion ModelsCode1
Kaleido-BERT: Vision-Language Pre-training on Fashion DomainCode1
A clinically motivated self-supervised approach for content-based image retrieval of CT liver imagesCode1
Deep Triplet Hashing Network for Case-based Medical Image RetrievalCode1
Delta Descriptors: Change-Based Place Representation for Robust Visual LocalizationCode1
Benchmarking Image Retrieval for Visual LocalizationCode1
CgAT: Center-Guided Adversarial Training for Deep Hashing-Based RetrievalCode1
CBVS: A Large-Scale Chinese Image-Text Benchmark for Real-World Short Video Search ScenariosCode1
AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-level RetrievalCode1
AutoLR: Layer-wise Pruning and Auto-tuning of Learning Rates in Fine-tuning of Deep NetworksCode1
Discriminative Region-based Multi-Label Zero-Shot LearningCode1
Divide&Classify: Fine-Grained Classification for City-Wide Visual Place RecognitionCode1
Divide&Classify: Fine-Grained Classification for City-Wide Visual Geo-LocalizationCode1
BEV-CV: Birds-Eye-View Transform for Cross-View Geo-LocalisationCode1
DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global FeaturesCode1
Beyond Cross-view Image Retrieval: Highly Accurate Vehicle Localization Using Satellite ImageCode1
Circle Loss: A Unified Perspective of Pair Similarity OptimizationCode1
Exploring Masked Autoencoders for Sensor-Agnostic Image Retrieval in Remote SensingCode1
Show:102550
← PrevPage 5 of 45Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SuperGlobalmAP80.2Unverified
2AMESmAP80Unverified
3Hypergraph propagation+community selectionmAP73Unverified
4TokenmAP66.57Unverified
5DELG+ α QE reranking+ RRT rerankingmAP64Unverified
6FIRemAP61.2Unverified
7HOWmAP56.9Unverified
8ResNet101+ArcFace GLDv2-train-cleanmAP51.6Unverified
9DELF–HQE+SPmAP50.3Unverified
10HesAff–rSIFT–HQE+SPmAP49.7Unverified
#ModelMetricClaimedVerifiedStatus
1AMESmAP90.7Unverified
2Hypergraph propagation+Community selectionmAP88.4Unverified
3TokenmAP82.28Unverified
4FIRemAP81.8Unverified
5DELG+ α QE reranking + RRT rerankingmAP80.4Unverified
6HOWmAP79.4Unverified
7ResNet101+ArcFace GLDv2-train-cleanmAP74.2Unverified
8DELF–HQE+SPmAP73.4Unverified
9HesAff–rSIFT–HQE+SPmAP71.3Unverified
10DELF–ASMK*+SPmAP67.8Unverified
#ModelMetricClaimedVerifiedStatus
1AMESmAP89.7Unverified
2SuperGlobalmAP86.7Unverified
3Hypergraph propagationmAP83.3Unverified
4TokenmAP78.56Unverified
5DELG+ α QE reranking + RRT rerankingmAP77.7Unverified
6ResNet101+ArcFace GLDv2-train-cleanmAP70.3Unverified
7FIRemAP70Unverified
8DELF–HQE+SPmAP69.3Unverified
9HOWmAP62.4Unverified
10R–R-MACmAP59.4Unverified
#ModelMetricClaimedVerifiedStatus
1AMESmAP94.9Unverified
2Hypergraph propagationmAP92.6Unverified
3TokenmAP89.34Unverified
4DELG+ α QE reranking + RRT rerankingmAP88.5Unverified
5FIRemAP85.3Unverified
6ResNet101+ArcFace GLDv2-train-cleanmAP84.9Unverified
7DELF–HQE+SPmAP84Unverified
8HOWmAP81.6Unverified
9R–R-MACmAP78.9Unverified
10R–GeMmAP77.2Unverified
#ModelMetricClaimedVerifiedStatus
1Swin-T (MosaiCLIP, CC-12M)Recall@1 (HN-Atom, UC)44.5Unverified
2RN-50 (MosaiCLIP, CC-12M)Recall@1 (HN-Atom, UC)44.4Unverified
3MosaiCLIP (YFCC-FT)Recall@1 (HN-Atom, UC)41.5Unverified
4RN-50 (NegCLIP, CC-12M)Recall@1 (HN-Atom, UC)41.4Unverified
5MosaiCLIP (CC-FT)Recall@1 (HN-Atom, UC)40.9Unverified
6Swin-T (NegCLIP, CC-12M)Recall@1 (HN-Atom, UC)39.6Unverified
7CLIP (YFCC-FT)Recall@1 (HN-Atom, UC)39.5Unverified
8ViT-L-14 (LAION400M)Recall@1 (HN-Atom + HN-Comp, SC)39.44Unverified
9NegCLIP (YFCC-FT)Recall@1 (HN-Atom, UC)39Unverified
10CLIP-FT (YFCC-FT)Recall@1 (HN-Atom, UC)38.3Unverified
#ModelMetricClaimedVerifiedStatus
1DQU-CIR(Recall@10+Recall@50)/271.77Unverified
2TMCIR(Recall@10+Recall@50)/266.56Unverified
3SPN4CIR (SPRC)(Recall@10+Recall@50)/266.41Unverified
4SPRC(Recall@10+Recall@50)/264.85Unverified
5Candidate Set Re-ranking(Recall@10+Recall@50)/262.15Unverified
6RUTIR (BLIP B/16)(Recall@10+Recall@50)/261.32Unverified
7CASE(Recall@10+Recall@50)/259.73Unverified
8CaLa(Recall@10+Recall@50)/257.96Unverified
9BLIP4CIR+Bi(Recall@10+Recall@50)/255.4Unverified
10CLIP4Cir (v3)(Recall@10+Recall@50)/255.36Unverified
#ModelMetricClaimedVerifiedStatus
1X-VLM (base)R@186.9Unverified
2RCARR@162.6Unverified
3SGRAFR@158.5Unverified
4LGSGMR@157.4Unverified
5VisualSpartaR@157.4Unverified
6TERAN MrSwR@156.5Unverified
7TERAN Symm.R@155.7Unverified
8VSRNR@154.7Unverified
9CAMPR@151.5Unverified
10SCAN i-tR@144Unverified
#ModelMetricClaimedVerifiedStatus
1TMCIR(Recall@5+Recall_subset@1)/283.46Unverified
2SPN4CIR (SPRC)(Recall@5+Recall_subset@1)/282.69Unverified
3SPRC2(Recall@5+Recall_subset@1)/282.66Unverified
4SPRC(Recall@5+Recall_subset@1)/281.39Unverified
5Candidate Set Re-ranking(Recall@5+Recall_subset@1)/280.9Unverified
6CaLa(Recall@5+Recall_subset@1)/278.74Unverified
7CASE (Pre-trained on LaSCo.Ca)(Recall@5+Recall_subset@1)/278.25Unverified
8CASE(Recall@5+Recall_subset@1)/277.5Unverified
9VISTA (base)(Recall@5+Recall_subset@1)/275.9Unverified
10MMRet-MLLM(Recall@5+Recall_subset@1)/275.7Unverified
#ModelMetricClaimedVerifiedStatus
1Unicom+ViT-L@336pxR@191.2Unverified
2ROADMAP (DeiT-B)R@186Unverified
3CGD (SG/GS)R@184.2Unverified
4ROADMAP (ResNet-50)R@183.1Unverified
5ProxyNCA++R@181.4Unverified
6PNP LossR@181.1Unverified
7Cross-Batch MemoryR@180.6Unverified
8Smooth-APR@180.1Unverified
9NormSoftmax2048 (ResNet-50)R@179.5Unverified
10EPSHN512R@178.3Unverified
#ModelMetricClaimedVerifiedStatus
1InternVL-G-FTR@185.9Unverified
2InternVL-C-FTR@185.2Unverified
3CN-CLIP (ViT-L/14@336px)R@184.4Unverified
4R2D2 (ViT-L/14)R@184.4Unverified
5CN-CLIP (ViT-H/14)R@183.8Unverified
6CN-CLIP (ViT-L/14)R@182.7Unverified
7CN-CLIP (ViT-B/16)R@179.1Unverified
8R2D2 (ViT-B)R@178.3Unverified
9Wukong (ViT-L/14)R@177.4Unverified
10Wukong (ViT-B/32)R@167.6Unverified
#ModelMetricClaimedVerifiedStatus
1Offline DiffusionMAP96.2Unverified
2CNN+IME layerMAP92Unverified
3DELF+FT+ATT+DIR+QEMAP90Unverified
4DIR+QE*MAP89Unverified