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

arXiv: https://arxiv.org/abs/2107.08000 · HTML: https://mlsanity.com/paper/2107.08000/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 59 references that are in the map.
- First posted on arXiv 16 Jul 2021.

## Builds on (most cited first, 30 of 46)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1910.03151/) (2019)
- [Fine-tuning CNN Image Retrieval with No Human Annotation](https://mlsanity.com/paper/1711.02512/) (2017)
- [Deep Metric Learning via Lifted Structured Feature Embedding](https://mlsanity.com/paper/1511.06452/) (2015)
- [Attention Augmented Convolutional Networks](https://mlsanity.com/paper/1904.09925/) (2019)
- [GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond](https://mlsanity.com/paper/1904.11492/) (2019)
- [Exploring Self-attention for Image Recognition](https://mlsanity.com/paper/2004.13621/) (2020)
- [Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval](https://mlsanity.com/paper/2004.01804/) (2020)
- [Dilated Residual Networks](https://mlsanity.com/paper/1705.09914/) (2017)
- [Large-Scale Image Retrieval with Attentive Deep Local Features](https://mlsanity.com/paper/1612.06321/) (2016)
- [Proxy Anchor Loss for Deep Metric Learning](https://mlsanity.com/paper/2003.13911/) (2020)
- [Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking](https://mlsanity.com/paper/1803.11285/) (2018)
- [Particular object retrieval with integral max-pooling of CNN activations](https://mlsanity.com/paper/1511.05879/) (2015)
- [Deep Image Retrieval: Learning global representations for image search](https://mlsanity.com/paper/1604.01325/) (2016)
- [Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks](https://mlsanity.com/paper/1810.12348/) (2018)
- [A2-Nets: Double Attention Networks](https://mlsanity.com/paper/1810.11579/) (2018)
- [End-to-end Learning of Deep Visual Representations for Image Retrieval](https://mlsanity.com/paper/1610.07940/) (2016)

## Built on by (most cited first, 12 of 12)

- [Boosting vision transformers for image retrieval](https://mlsanity.com/paper/2210.11909/) (2022)
- [Vision Transformers: From Semantic Segmentation to Dense Prediction](https://mlsanity.com/paper/2207.09339/) (2022)
- [On Train-Test Class Overlap and Detection for Image Retrieval](https://mlsanity.com/paper/2404.01524/) (2024)
- [TSGAN: An Optical-to-SAR Dual Conditional GAN for Optical based SAR Temporal Shifting](https://mlsanity.com/paper/2401.00440/) (2023)
- [Applications of Explainable artificial intelligence in Earth system science](https://mlsanity.com/paper/2406.11882/) (2024)
- [Attention-Based Scattering Network for Satellite Imagery](https://mlsanity.com/paper/2210.12185/) (2022)
- [Conditional Cross Attention Network for Multi-Space Embedding without Entanglement in Only a SINGLE Network](https://mlsanity.com/paper/2307.13254/) (2023)
- [Enhancing Landmark Detection in Cluttered Real-World Scenarios with Vision Transformers](https://mlsanity.com/paper/2308.13671/) (2023)
- [M3BUNet: Mobile Mean Max UNet for Pancreas Segmentation on CT-Scans](https://mlsanity.com/paper/2401.10419/) (2024)
- [UAVPairs: A Challenging Benchmark for Match Pair Retrieval of Large-scale UAV Images](https://mlsanity.com/paper/2505.22098/) (2025)
- [BrainSegNet: A Novel Framework for Whole-Brain MRI Parcellation Enhanced by Large Models](https://mlsanity.com/paper/2601.09263/) (2026)
- [Reliable iToF Depth Sensing via Sensor-Intrinsic Uncertainty Modeling and State-Space Restoration](https://mlsanity.com/paper/2609.05507/) (2026)

## 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.