# Attention-based Pyramid Aggregation Network for Visual Place Recognition

arXiv: https://arxiv.org/abs/1808.00288 · HTML: https://mlsanity.com/paper/1808.00288/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Aug 2018.

## 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)
- [Rethinking Visual Geo-localization for Large-Scale Applications](https://mlsanity.com/paper/2204.02287/) (2022)
- [EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition](https://mlsanity.com/paper/2308.10832/) (2023)
- [Deep Visual Geo-localization Benchmark](https://mlsanity.com/paper/2204.03444/) (2022)
- [Are Local Features All You Need for Cross-Domain Visual Place Recognition?](https://mlsanity.com/paper/2304.05887/) (2023)
- [AddressCLIP: Empowering Vision-Language Models for City-wide Image Address Localization](https://mlsanity.com/paper/2407.08156/) (2024)
- [Semantic Reinforced Attention Learning for Visual Place Recognition](https://mlsanity.com/paper/2108.08443/) (2021)
- [MultiRes-NetVLAD: Augmenting Place Recognition Training with Low-Resolution Imagery](https://mlsanity.com/paper/2202.09146/) (2022)
- [STUN: Self-Teaching Uncertainty Estimation for Place Recognition](https://mlsanity.com/paper/2203.01851/) (2022)
- [Learning Semantics for Visual Place Recognition through Multi-Scale Attention](https://mlsanity.com/paper/2201.09701/) (2022)
- [VOLoc: Visual Place Recognition by Querying Compressed Lidar Map](https://mlsanity.com/paper/2402.15961/) (2024)
- [Unifying Local and Global Multimodal Features for Place Recognition in Aliased and Low-Texture Environments](https://mlsanity.com/paper/2403.13395/) (2024)
- [ProGEO: Generating Prompts through Image-Text Contrastive Learning for Visual Geo-localization](https://mlsanity.com/paper/2406.01906/) (2024)
- [Monocular visual simultaneous localization and mapping: (r)evolution from geometry to deep learning-based pipelines](https://mlsanity.com/paper/2503.02955/) (2025)
- [Patch-NetVLAD+: Learned patch descriptor and weighted matching strategy for place recognition](https://mlsanity.com/paper/2202.05738/) (2022)
- [VLAD-BuFF: Burst-aware Fast Feature Aggregation for Visual Place Recognition](https://mlsanity.com/paper/2409.19293/) (2024)
- [ClusVPR: Efficient Visual Place Recognition with Clustering-based Weighted Transformer](https://mlsanity.com/paper/2310.04099/) (2023)
- [VIPeR: Visual Incremental Place Recognition with Adaptive Mining and Continual Learning](https://mlsanity.com/paper/2407.21416/) (2024)
- [Why-So-Deep: Towards Boosting Previously Trained Models for Visual Place Recognition](https://mlsanity.com/paper/2201.03212/) (2022)
- [Uncertainty-Aware DNN for Multi-Modal Camera Localization](https://mlsanity.com/paper/2211.01234/) (2022)
- [SaRPFF: A Self-Attention with Register-based Pyramid Feature Fusion module for enhanced RLD detection](https://mlsanity.com/paper/2402.16291/) (2024)

## Abstract (arXiv)

Visual place recognition is challenging in the urban environment and is usually viewed as a large scale image retrieval task. The intrinsic challenges in place recognition exist that the confusing objects such as cars and trees frequently occur in the complex urban scene, and buildings with repetitive structures may cause over-counting and the burstiness problem degrading the image representations. To address these problems, we present an Attention-based Pyramid Aggregation Network (APANet), which is trained in an end-to-end manner for place recognition. One main component of APANet, the spatial pyramid pooling, can effectively encode the multi-size buildings containing geo-information. The other one, the attention block, is adopted as a region evaluator for suppressing the confusing regional features while highlighting the discriminative ones. When testing, we further propose a simple yet effective PCA power whitening strategy, which significantly improves the widely used PCA whitening by reasonably limiting the impact of over-counting. Experimental evaluations demonstrate that the proposed APANet outperforms the state-of-the-art methods on two place recognition benchmarks, and generalizes well on standard image retrieval datasets.