mlsanityData to 7 Oct 2026

All the attention you need: Global-local, spatial-channel attention for image retrieval

arXiv 2107.08000 ↗First posted 16 Jul 2021cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

We address representation learning for large-scale instance-level image retrieval. Apart from backbone, training pipelines and loss functions, popular approaches have focused on different spatial pooling and attention mechanisms, which are at the core of learning a powerful global image representation. There are different forms of attention according to the interaction of elements of the feature tensor (local and global) and the dimensions where it is applied (spatial and channel). Unfortunately, each study addresses only one or two forms of attention and applies it to different problems like classification, detection or retrieval. We present global-local attention module (GLAM), which is attached at the end of a backbone network and incorporates all four forms of attention: local and global, spatial and channel. We obtain a new feature tensor and, by spatial pooling, we learn a powerful embedding for image retrieval. Focusing on global descriptors, we provide empirical evidence of the interaction of all forms of attention and improve the state of the art on standard benchmarks.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 46 of its 59 references that are in the map. First posted on arXiv 16 Jul 2021.

Builds on

46 of 59 references.

References · 46

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2017Squeeze-and-Excitation Networkscited by 4,763
  7. 2014Going Deeper with Convolutionscited by 4,231
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  9. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  10. 2017Non-local Neural Networkscited by 2,290
  11. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  12. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
34 more
  1. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  2. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 935
  3. 2019ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networkscited by 572
  4. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 497
  5. 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
  6. 2019Attention Augmented Convolutional Networkscited by 363
  7. 2019GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyondcited by 331
  8. 2020Exploring Self-attention for Image Recognitioncited by 313
  9. 2020Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrievalcited by 305
  10. 2017Dilated Residual Networkscited by 293
  11. 2016Large-Scale Image Retrieval with Attentive Deep Local Featurescited by 238
  12. 2020Proxy Anchor Loss for Deep Metric Learningcited by 195
  13. 2018Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarkingcited by 189
  14. 2015Particular object retrieval with integral max-pooling of CNN activationscited by 160
  15. 2016Deep Image Retrieval: Learning global representations for image searchcited by 147
  16. 2018Gather-Excite: Exploiting Feature Context in Convolutional Neural Networkscited by 138
  17. 2018A2-Nets: Double Attention Networkscited by 136
  18. 2016End-to-end Learning of Deep Visual Representations for Image Retrievalcited by 122
  19. 2018Neural Nearest Neighbors Networkscited by 98
  20. 2021Training Vision Transformers for Image Retrievalcited by 90
  21. 2018Global Second-order Pooling Convolutional Networkscited by 66
  22. 2015Aggregating Deep Convolutional Features for Image Retrievalcited by 63
  23. 2016CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examplescited by 58
  24. 2020Learning and aggregating deep local descriptors for instance-level recognitioncited by 54
  25. 2016Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representationscited by 49
  26. 2014Visual Instance Retrieval with Deep Convolutional Networkscited by 48
  27. 2020SOLAR: Second-Order Loss and Attention for Image Retrievalcited by 45
  28. 2015Cross-dimensional Weighting for Aggregated Deep Convolutional Featurescited by 41
  29. 2018Detect-to-Retrieve: Efficient Regional Aggregation for Image Searchcited by 39
  30. 2019Local Features and Visual Words Emerge in Activationscited by 36
  31. 2018Efficient Image Retrieval via Decoupling Diffusion into Online and Offline Processingcited by 20
  32. 2020Two-stage Discriminative Re-ranking for Large-scale Landmark Retrievalcited by 18
  33. 2018Attention-Aware Generalized Mean Pooling for Image Retrievalcited by 12
  34. 2017Class-Weighted Convolutional Features for Visual Instance Searchcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 3; 2024: 3; 2025: 1; 2026: 2.

12 papers.

  1. 2022Boosting vision transformers for image retrievalcited by 19
  2. 2022Vision Transformers: From Semantic Segmentation to Dense Predictioncited by 6
  3. 2024On Train-Test Class Overlap and Detection for Image Retrievalcited by 3
  4. 2023TSGAN: An Optical-to-SAR Dual Conditional GAN for Optical based SAR Temporal Shiftingcited by 2
  5. 2024Applications of Explainable artificial intelligence in Earth system sciencecited by 1
  6. 2022Attention-Based Scattering Network for Satellite Imagerycited by 0
  7. 2023Conditional Cross Attention Network for Multi-Space Embedding without Entanglement in Only a SINGLE Networkcited by 0
  8. 2023Enhancing Landmark Detection in Cluttered Real-World Scenarios with Vision Transformerscited by 0
  9. 2024M3BUNet: Mobile Mean Max UNet for Pancreas Segmentation on CT-Scanscited by 0
  10. 2025UAVPairs: A Challenging Benchmark for Match Pair Retrieval of Large-scale UAV Imagescited by 0
  11. 2026BrainSegNet: A Novel Framework for Whole-Brain MRI Parcellation Enhanced by Large Modelscited by 0
  12. 2026Reliable iToF Depth Sensing via Sensor-Intrinsic Uncertainty Modeling and State-Space Restorationcited by 0