mlsanityData to 14 Oct 2026

Deep Learning for Instance Retrieval: A Survey

arXiv 2101.11282 ↗First posted 27 Jan 2021cs.CVcited by 70

Not on the map. Why?

Abstract (arXiv)

In recent years a vast amount of visual content has been generated and shared from many fields, such as social media platforms, medical imaging, and robotics. This abundance of content creation and sharing has introduced new challenges, particularly that of searching databases for similar content-Content Based Image Retrieval (CBIR)-a long-established research area in which improved efficiency and accuracy are needed for real-time retrieval. Artificial intelligence has made progress in CBIR and has significantly facilitated the process of instance search. In this survey we review recent instance retrieval works that are developed based on deep learning algorithms and techniques, with the survey organized by deep network architecture types, deep features, feature embedding and aggregation methods, and network fine-tuning strategies. Our survey considers a wide variety of recent methods, whereby we identify milestone work, reveal connections among various methods and present the commonly used benchmarks, evaluation results, common challenges, and propose promising future directions.

Key facts. Cited by 70 papers in the map (data through 14 Oct 2026). Builds on 80 of its 171 references that are in the map. First posted on arXiv 27 Jan 2021.

Builds on

80 of 171 references.

References · 80

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2014Going Deeper with Convolutionscited by 4,241
  6. 2014How transferable are features in deep neural networks?cited by 1,225
  7. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,028
  8. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 941
  9. 2020Image Segmentation Using Deep Learning: A Surveycited by 660
  10. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 499
  11. 2018Deep Learning for Generic Object Detection: A Surveycited by 392
  12. 2019Multi-Similarity Loss with General Pair Weighting for Deep Metric Learningcited by 368
38 more
  1. 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 326
  2. 2020A Metric Learning Reality Checkcited by 321
  3. 2014CNN Features off-the-shelf: an Astounding Baseline for Recognitioncited by 316
  4. 2020Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrievalcited by 309
  5. 2016Large-Scale Image Retrieval with Attentive Deep Local Featurescited by 238
  6. 2013OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networkscited by 224
  7. 2019A Survey of the Recent Architectures of Deep Convolutional Neural Networkscited by 213
  8. 2017Working hard to know your neighbor's margins: Local descriptor learning losscited by 212
  9. 2018Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarkingcited by 191
  10. 2014Learning Fine-grained Image Similarity with Deep Rankingcited by 190
  11. 2019Learning with Average Precision: Training Image Retrieval with a Listwise Losscited by 185
  12. 2015Particular object retrieval with integral max-pooling of CNN activationscited by 161
  13. 2016Deep Image Retrieval: Learning global representations for image searchcited by 147
  14. 2014Return of the Devil in the Details: Delving Deep into Convolutional Netscited by 122
  15. 2016End-to-end Learning of Deep Visual Representations for Image Retrievalcited by 122
  16. 2016A Survey on Learning to Hashcited by 119
  17. 2020A unifying mutual information view of metric learning: cross-entropy vs. pairwise lossescited by 100
  18. 2020Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrievalcited by 98
  19. 2016SIFT Meets CNN: A Decade Survey of Instance Retrievalcited by 67
  20. 2015Aggregating Deep Convolutional Features for Image Retrievalcited by 63
  21. 2016CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examplescited by 58
  22. 2020Learning and aggregating deep local descriptors for instance-level recognitioncited by 55
  23. 2017Few-Shot Learning Through an Information Retrieval Lenscited by 51
  24. 2016Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representationscited by 50
  25. 2014Visual Instance Retrieval with Deep Convolutional Networkscited by 48
  26. 2014Convolutional Kernel Networkscited by 47
  27. 2020SOLAR: Second-Order Loss and Attention for Image Retrievalcited by 45
  28. 2015Cross-dimensional Weighting for Aggregated Deep Convolutional Featurescited by 42
  29. 2018Detect-to-Retrieve: Efficient Regional Aggregation for Image Searchcited by 39
  30. 2014Multi-scale Orderless Pooling of Deep Convolutional Activation Featurescited by 38
  31. 2019Local Features and Visual Words Emerge in Activationscited by 37
  32. 2018Mining on Manifolds: Metric Learning without Labelscited by 36
  33. 2018Universal Perturbation Attack Against Image Retrievalcited by 32
  34. 2019Targeted Mismatch Adversarial Attack: Query with a Flower to Retrieve the Towercited by 26
  35. 2017Recent Advance in Content-based Image Retrieval: A Literature Surveycited by 24
  36. 2018Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processingcited by 20
  37. 2018Matchable Image Retrieval by Learning from Surface Reconstructioncited by 19
  38. 2020Two-stage Discriminative Re-ranking for Large-scale Landmark Retrievalcited by 18

50 most cited of 80 All 80 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 6; 2023: 26; 2024: 16; 2025: 18; 2026: 4.

70 papers.

Sort:

By area:

  1. 2022Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Modelscited by 424
  2. 2023MixVPR: Feature Mixing for Visual Place Recognitioncited by 161
  3. 2023MatFormer: Nested Transformer for Elastic Inferencecited by 85
  4. 2024Speculative RAG: Enhancing Retrieval Augmented Generation through Draftingcited by 77
  5. 2023Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Taskscited by 72
  6. 2023Global Features are All You Need for Image Retrieval and Rerankingcited by 41
  7. 2022Handcrafted Histological Transformer (H2T): Unsupervised Representation of Whole Slide Imagescited by 32
  8. 2024Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localizationcited by 31
  9. 2023POPE: 6-DoF Promptable Pose Estimation of Any Object, in Any Scene, with One Referencecited by 30
  10. 2023Towards Universal Image Embeddings: A Large-Scale Dataset and Challenge for Generic Image Representationscited by 28
  11. 2024Close, But Not There: Boosting Geographic Distance Sensitivity in Visual Place Recognitioncited by 27
  12. 2023Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrievalcited by 22
38 more
  1. 2023Controllable Textual Inversion for Personalized Text-to-Image Generationcited by 14
  2. 2025Uni-Retrieval: A Multi-Style Retrieval Framework for STEM's Educationcited by 13
  3. 2023SAAN: Similarity-aware attention flow network for change detection with VHR remote sensing imagescited by 12
  4. 2023Have We Ever Encountered This Before? Retrieving Out-of-Distribution Road Obstacles from Driving Scenescited by 9
  5. 2023VoxDet: Voxel Learning for Novel Instance Detectioncited by 8
  6. 2023Let All be Whitened: Multi-teacher Distillation for Efficient Visual Retrievalcited by 7
  7. 2024Analysis and Validation of Image Search Engines in Histopathologycited by 7
  8. 2024LInK: Learning Joint Representations of Design and Performance Spaces through Contrastive Learning for Mechanism Synthesiscited by 7
  9. 2024Zero-shot Composed Image Retrieval Considering Query-target Relationship Leveraging Masked Image-text Pairscited by 7
  10. 2024MatMamba: A Matryoshka State Space Modelcited by 7
  11. 2025ConText-CIR: Learning from Concepts in Text for Composed Image Retrievalcited by 7
  12. 2023Region-based Contrastive Pretraining for Medical Image Retrieval with Anatomic Querycited by 6
  13. 2024Learning Unknowns from Unknowns: Diversified Negative Prototypes Generator for Few-Shot Open-Set Recognitioncited by 6
  14. 2023PanoVPR: Towards Unified Perspective-to-Equirectangular Visual Place Recognition via Sliding Windows across the Panoramic Viewcited by 5
  15. 2022A Flexible Nadaraya-Watson Head Can Offer Explainable and Calibrated Classificationcited by 4
  16. 2023Leveraging BEV Representation for 360-degree Visual Place Recognitioncited by 4
  17. 2024Evaluating Pre-trained Convolutional Neural Networks and Foundation Models as Feature Extractors for Content-based Medical Image Retrievalcited by 4
  18. 2025Learning Along the Arrow of Time: Hyperbolic Geometry for Backward-Compatible Representation Learningcited by 4
  19. 2025On the rankability of visual embeddingscited by 4
  20. 2023Dsfer-Net: A Deep Supervision and Feature Retrieval Network for Bitemporal Change Detection Using Modern Hopfield Networkscited by 3
  21. 2023TReR: A Lightweight Transformer Re-Ranking Approach for 3D LiDAR Place Recognitioncited by 3
  22. 2023Integrating Visual and Semantic Similarity Using Hierarchies for Image Retrievalcited by 3
  23. 2024ShelfHelp: Empowering Humans to Perform Vision-Independent Manipulation Tasks with a Socially Assistive Robotic Canecited by 3
  24. 2025Anonymization of Documents for Law Enforcement with Machine Learningcited by 3
  25. 2025Cross-Problem Parameter Transfer in Quantum Approximate Optimization Algorithm: A Machine Learning Approachcited by 3
  26. 2022MMFL-Net: Multi-scale and Multi-granularity Feature Learning for Cross-domain Fashion Retrievalcited by 2
  27. 2023Efficient Scopeformer: Towards Scalable and Rich Feature Extraction for Intracranial Hemorrhage Detectioncited by 2
  28. 2023Retail-786k: a Large-Scale Dataset for Visual Entity Matchingcited by 2
  29. 2024Enhancing Historical Image Retrieval with Compositional Cuescited by 2
  30. 2024DREW : Towards Robust Data Provenance by Leveraging Error-Controlled Watermarkingcited by 2
  31. 2025SCING:Towards More Efficient and Robust Person Re-Identification through Selective Cross-modal Prompt Tuningcited by 2
  32. 2025From Query to Explanation: Uni-RAG for Multi-Modal Retrieval-Augmented Learning in STEMcited by 2
  33. 2025Finer-Personalization Rank: Fine-Grained Retrieval Examines Identity Preservation for Personalized Generationcited by 2
  34. 2023Class-Specific Variational Auto-Encoder for Content-Based Image Retrievalcited by 1
  35. 2023Decompose Semantic Shifts for Composed Image Retrievalcited by 1
  36. 2023A survey of manifold learning and its applications for multimediacited by 1
  37. 2025Circuit Diagram Retrieval Based on Hierarchical Circuit Graph Representationcited by 1
  38. 2025Training-free Conditional Image Embedding Framework Leveraging Large Vision Language Modelscited by 1

50 most cited of 70 All 70 (JSON)