mlsanityData to 7 Oct 2026

On Train-Test Class Overlap and Detection for Image Retrieval

arXiv 2404.01524 ↗First posted 1 Apr 2024cs.CV cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

How important is it for training and evaluation sets to not have class overlap in image retrieval? We revisit Google Landmarks v2 clean, the most popular training set, by identifying and removing class overlap with Revisited Oxford and Paris [34], the most popular evaluation set. By comparing the original and the new RGLDv2-clean on a benchmark of reproduced state-of-the-art methods, our findings are striking. Not only is there a dramatic drop in performance, but it is inconsistent across methods, changing the ranking.What does it take to focus on objects or interest and ignore background clutter when indexing? Do we need to train an object detector and the representation separately? Do we need location supervision? We introduce Single-stage Detect-to-Retrieve (CiDeR), an end-to-end, single-stage pipeline to detect objects of interest and extract a global image representation. We outperform previous state-of-the-art on both existing training sets and the new RGLDv2-clean. Our dataset is available at https://github.com/dealicious-inc/RGLDv2-clean.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 43 of its 64 references that are in the map. First posted on arXiv 1 Apr 2024.

Builds on

43 of 64 references.

References · 43

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  6. 2017Squeeze-and-Excitation Networkscited by 4,763
  7. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  8. 2017Non-local Neural Networkscited by 2,290
  9. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  10. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  11. 2021Scaling Vision Transformerscited by 993
  12. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 636
31 more
  1. 2019ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networkscited by 572
  2. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 497
  3. 2018Bag of Tricks for Image Classification with Convolutional Neural Networkscited by 430
  4. 2019Selective Kernel Networkscited by 401
  5. 2020Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrievalcited by 305
  6. 2016Large-Scale Image Retrieval with Attentive Deep Local Featurescited by 238
  7. 2018Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarkingcited by 189
  8. 2015Particular object retrieval with integral max-pooling of CNN activationscited by 160
  9. 2016Deep Image Retrieval: Learning global representations for image searchcited by 147
  10. 2018Gather-Excite: Exploiting Feature Context in Convolutional Neural Networkscited by 138
  11. 2015Aggregating Deep Convolutional Features for Image Retrievalcited by 63
  12. 2016CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examplescited by 58
  13. 2020Learning and aggregating deep local descriptors for instance-level recognitioncited by 54
  14. 2021DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Featurescited by 54
  15. 2014Visual Instance Retrieval with Deep Convolutional Networkscited by 48
  16. 2022Correlation Verification for Image Retrievalcited by 47
  17. 2020SOLAR: Second-Order Loss and Attention for Image Retrievalcited by 45
  18. 2015Cross-dimensional Weighting for Aggregated Deep Convolutional Featurescited by 41
  19. 2018Detect-to-Retrieve: Efficient Regional Aggregation for Image Searchcited by 39
  20. 2019Local Features and Visual Words Emerge in Activationscited by 36
  21. 2022Learning Super-Features for Image Retrievalcited by 35
  22. 2021Augmenting Convolutional networks with attention-based aggregationcited by 29
  23. 2022Boosting vision transformers for image retrievalcited by 19
  24. 2020Two-stage Discriminative Re-ranking for Large-scale Landmark Retrievalcited by 18
  25. 2023Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?cited by 16
  26. 2016Faster R-CNN Features for Instance Searchcited by 14
  27. 2018Attention-Aware Generalized Mean Pooling for Image Retrievalcited by 12
  28. 2021All the attention you need: Global-local, spatial-channel attention for image retrievalcited by 12
  29. 2021Learning Token-based Representation for Image Retrievalcited by 10
  30. 2015Object Level Deep Feature Pooling for Compact Image Representationcited by 3
  31. 2016What Is the Best Practice for CNNs Applied to Visual Instance Retrieval?cited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 1.

3 papers.

  1. 2025ILIAS: Instance-Level Image retrieval At Scalecited by 29
  2. 2024AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-level Retrievalcited by 16
  3. 2026Data Leakage in Automotive Perception: Practitioners' Insightscited by 0