# Attention-Aware Generalized Mean Pooling for Image Retrieval

arXiv: https://arxiv.org/abs/1811.00202 · HTML: https://mlsanity.com/paper/1811.00202/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Nov 2018.

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

- [SDPL: Shifting-Dense Partition Learning for UAV-View Geo-Localization](https://mlsanity.com/paper/2403.04172/) (2024)
- [Boosting vision transformers for image retrieval](https://mlsanity.com/paper/2210.11909/) (2022)
- [All the attention you need: Global-local, spatial-channel attention for image retrieval](https://mlsanity.com/paper/2107.08000/) (2021)
- [On Train-Test Class Overlap and Detection for Image Retrieval](https://mlsanity.com/paper/2404.01524/) (2024)
- [CLASH: Complementary Learning with Neural Architecture Search for Gait Recognition](https://mlsanity.com/paper/2407.03632/) (2024)
- [3rd Place Solution to Google Landmark Recognition Competition 2021](https://mlsanity.com/paper/2110.02794/) (2021)
- [Adversarial Learning of Hard Positives for Place Recognition](https://mlsanity.com/paper/2205.03871/) (2022)
- [2nd Place Solution to Google Landmark Recognition Competition 2021](https://mlsanity.com/paper/2110.02638/) (2021)
- [Annotation Efficient Person Re-Identification with Diverse Cluster-Based Pair Selection](https://mlsanity.com/paper/2203.05395/) (2022)
- [A Novel Dual-pooling Attention Module for UAV Vehicle Re-identification](https://mlsanity.com/paper/2306.14104/) (2023)
- [AaP-ReID: Improved Attention-Aware Person Re-identification](https://mlsanity.com/paper/2309.15780/) (2023)
- [Geometric Mean Pooling for Equal-Weight Multiplicative Coarse-Graining](https://mlsanity.com/paper/2609.21876/) (2026)

## Abstract (arXiv)

It has been shown that image descriptors extracted by convolutional neural networks (CNNs) achieve remarkable results for retrieval problems. In this paper, we apply attention mechanism to CNN, which aims at enhancing more relevant features that correspond to important keypoints in the input image. The generated attention-aware features are then aggregated by the previous state-of-the-art generalized mean (GeM) pooling followed by normalization to produce a compact global descriptor, which can be efficiently compared to other image descriptors by the dot product. An extensive comparison of our proposed approach with state-of-the-art methods is performed on the new challenging ROxford5k and RParis6k retrieval benchmarks. Results indicate significant improvement over previous work. In particular, our attention-aware GeM (AGeM) descriptor outperforms state-of-the-art method on ROxford5k under the `Hard' evaluation protocal.