# Attention-Based Query Expansion Learning

arXiv: https://arxiv.org/abs/2007.08019 · HTML: https://mlsanity.com/paper/2007.08019/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jul 2020.

## Built on by (most cited first, 21 of 21)

- [Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition](https://mlsanity.com/paper/2103.01486/) (2021)
- [Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers](https://mlsanity.com/paper/2103.16553/) (2021)
- [Global Features are All You Need for Image Retrieval and Reranking](https://mlsanity.com/paper/2308.06954/) (2023)
- [DnS: Distill-and-Select for Efficient and Accurate Video Indexing and Retrieval](https://mlsanity.com/paper/2106.13266/) (2021)
- [Contextual Similarity Aggregation with Self-attention for Visual Re-ranking](https://mlsanity.com/paper/2110.13430/) (2021)
- [Instance-Level Composed Image Retrieval](https://mlsanity.com/paper/2510.25387/) (2025)
- [Multi-Query Video Retrieval](https://mlsanity.com/paper/2201.03639/) (2022)
- [RELOCATE: A Simple Training-Free Baseline for Visual Query Localization Using Region-Based Representations](https://mlsanity.com/paper/2412.01826/) (2024)
- [A Memory Transformer Network for Incremental Learning](https://mlsanity.com/paper/2210.04485/) (2022)
- [Learnable Pillar-based Re-ranking for Image-Text Retrieval](https://mlsanity.com/paper/2304.12570/) (2023)
- [Towards Writer Retrieval for Historical Datasets](https://mlsanity.com/paper/2305.05358/) (2023)
- [LOCORE: Image Re-ranking with Long-Context Sequence Modeling](https://mlsanity.com/paper/2503.21772/) (2025)
- [CarGait: Cross-Attention based Re-ranking for Gait recognition](https://mlsanity.com/paper/2503.03501/) (2025)
- [Cluster-Aware Similarity Diffusion for Instance Retrieval](https://mlsanity.com/paper/2406.02343/) (2024)
- [Enhancing Geo-localization for Crowdsourced Flood Imagery via LLM-Guided Attention](https://mlsanity.com/paper/2512.11811/) (2025)
- [ELViS: Efficient Visual Similarity from Local Descriptors that Generalizes Across Domains](https://mlsanity.com/paper/2603.28603/) (2026)
- [Learning Query Expansion over the Nearest Neighbor Graph](https://mlsanity.com/paper/2112.02666/) (2021)
- [Accurate and Fast Pixel Retrieval with Spatial and Uncertainty Aware Hypergraph Diffusion](https://mlsanity.com/paper/2406.11242/) (2024)
- [Enhancing Visual Re-ranking through Denoising Nearest Neighbor Graph via Continuous CRF](https://mlsanity.com/paper/2412.13875/) (2024)
- [Visual Re-Ranking with Non-Visual Side Information](https://mlsanity.com/paper/2504.11134/) (2025)
- [Locality Preserving Markovian Transition for Instance Retrieval](https://mlsanity.com/paper/2506.05196/) (2025)

## Abstract (arXiv)

Query expansion is a technique widely used in image search consisting in combining highly ranked images from an original query into an expanded query that is then reissued, generally leading to increased recall and precision. An important aspect of query expansion is choosing an appropriate way to combine the images into a new query. Interestingly, despite the undeniable empirical success of query expansion, ad-hoc methods with different caveats have dominated the landscape, and not a lot of research has been done on learning how to do query expansion. In this paper we propose a more principled framework to query expansion, where one trains, in a discriminative manner, a model that learns how images should be aggregated to form the expanded query. Within this framework, we propose a model that leverages a self-attention mechanism to effectively learn how to transfer information between the different images before aggregating them. Our approach obtains higher accuracy than existing approaches on standard benchmarks. More importantly, our approach is the only one that consistently shows high accuracy under different regimes, overcoming caveats of existing methods.