mlsanityData to 7 Oct 2026

CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples

arXiv 1604.02426 ↗First posted 8 Apr 2016cs.CVcited by 58

Not on the map. Why?

Abstract (arXiv)

Convolutional Neural Networks (CNNs) achieve state-of-the-art performance in many computer vision tasks. However, this achievement is preceded by extreme manual annotation in order to perform either training from scratch or fine-tuning for the target task. In this work, we propose to fine-tune CNN for image retrieval from a large collection of unordered images in a fully automated manner. We employ state-of-the-art retrieval and Structure-from-Motion (SfM) methods to obtain 3D models, which are used to guide the selection of the training data for CNN fine-tuning. We show that both hard positive and hard negative examples enhance the final performance in particular object retrieval with compact codes.

Key facts. Cited by 58 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Apr 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 19; 2023: 10; 2024: 8; 2025: 2; 2026: 2.

58 papers.

Sort:

By area:

  1. 2022Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Modelscited by 418
  2. 2022A Self-Supervised Descriptor for Image Copy Detectioncited by 175
  3. 2022Map-free Visual Relocalization: Metric Pose Relative to a Single Imagecited by 112
  4. 2022Deep Visual Geo-localization Benchmarkcited by 83
  5. 2022ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similaritycited by 82
  6. 2021Deep Learning for Instance Retrieval: A Surveycited by 70
  7. 2021DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Featurescited by 54
  8. 2022Correlation Verification for Image Retrievalcited by 47
  9. 2021Visual Grounding with Transformerscited by 42
  10. 2021Interpretable Semantic Photo Geolocationcited by 32
  11. 2024Close, But Not There: Boosting Geographic Distance Sensitivity in Visual Place Recognitioncited by 27
  12. 2023HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformercited by 26
38 more
  1. 2024Composed Video Retrieval via Enriched Context and Discriminative Embeddingscited by 26
  2. 2022DQ-DETR: Dual Query Detection Transformer for Phrase Extraction and Groundingcited by 24
  3. 2021Reassessing the Limitations of CNN Methods for Camera Pose Regressioncited by 19
  4. 2021Semantic Reinforced Attention Learning for Visual Place Recognitioncited by 19
  5. 2021Robust and Decomposable Average Precision for Image Retrievalcited by 19
  6. 2022Boosting vision transformers for image retrievalcited by 19
  7. 2022Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Surveycited by 17
  8. 2021All the attention you need: Global-local, spatial-channel attention for image retrievalcited by 12
  9. 2021InsCLR: Improving Instance Retrieval with Self-Supervisioncited by 11
  10. 2023FashionNTM: Multi-turn Fashion Image Retrieval via Cascaded Memorycited by 11
  11. 2022FeDXL: Provable Federated Learning for Deep X-Risk Optimizationcited by 10
  12. 2023Optimization of Rank Losses for Image Retrievalcited by 10
  13. 2023Confidence-based Visual Dispersal for Few-shot Unsupervised Domain Adaptationcited by 9
  14. 2021GAM: Explainable Visual Similarity and Classification via Gradient Activation Mapscited by 8
  15. 2022Hierarchical Average Precision Training for Pertinent Image Retrievalcited by 8
  16. 2022A Critical Analysis of Image-based Camera Pose Estimation Techniquescited by 7
  17. 2021Visual Correspondence Hallucinationcited by 5
  18. 20224Seasons: Benchmarking Visual SLAM and Long-Term Localization for Autonomous Driving in Challenging Conditionscited by 5
  19. 2023AffineGlue: Joint Matching and Robust Estimationcited by 5
  20. 2023Object-Centric Open-Vocabulary Image-Retrieval with Aggregated Featurescited by 5
  21. 2021Rethinking the Optimization of Average Precision: Only Penalizing Negative Instances before Positive Ones is Enoughcited by 4
  22. 2021Evaluating Contrastive Models for Instance-based Image Retrievalcited by 4
  23. 2022BOSS: Bottom-up Cross-modal Semantic Composition with Hybrid Counterfactual Training for Robust Content-based Image Retrievalcited by 4
  24. 2021Digging Into Self-Supervised Learning of Feature Descriptorscited by 3
  25. 2023Dark Side Augmentation: Generating Diverse Night Examples for Metric Learningcited by 3
  26. 2024On Train-Test Class Overlap and Detection for Image Retrievalcited by 3
  27. 2021AugNet: End-to-End Unsupervised Visual Representation Learning with Image Augmentationcited by 2
  28. 2021Homography augumented momentum constrastive learning for SAR image retrievalcited by 2
  29. 2021Construct Informative Triplet with Two-stage Hard-sample Generationcited by 2
  30. 2022Adversarial Learning of Hard Positives for Place Recognitioncited by 2
  31. 2024CriSp: Leveraging Tread Depth Maps for Enhanced Crime-Scene Shoeprint Matchingcited by 2
  32. 2024NaVIP: An Image-Centric Indoor Navigation Solution for Visually Impaired Peoplecited by 2
  33. 2022Reuse your features: unifying retrieval and feature-metric alignmentcited by 1
  34. 2024A Hyperdimensional One Place Signature to Represent Them All: Stackable Descriptors For Visual Place Recognitioncited by 1
  35. 2026SupScene: Scene-Structured Overlap Supervision for Image Retrieval in Unconstrained SfMcited by 1
  36. 2022Learning Deep Representations via Contrastive Learning for Instance Retrievalcited by 0
  37. 2022Supervised Fine-tuning Evaluation for Long-term Visual Place Recognitioncited by 0
  38. 2022SuperGF: Unifying Local and Global Features for Visual Localizationcited by 0

50 most cited of 58 All 58 (JSON)