# Adversarial Learning of Hard Positives for Place Recognition

arXiv: https://arxiv.org/abs/2205.03871 · HTML: https://mlsanity.com/paper/2205.03871/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 32 references that are in the map.
- First posted on arXiv 8 May 2022.

## Builds on (most cited first, 16 of 16)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018)
- [Fine-tuning CNN Image Retrieval with No Human Annotation](https://mlsanity.com/paper/1711.02512/) (2017)
- [Large-Scale Evolution of Image Classifiers](https://mlsanity.com/paper/1703.01041/) (2017)
- [Large-Scale Image Retrieval with Attentive Deep Local Features](https://mlsanity.com/paper/1612.06321/) (2016)
- [Learning with Average Precision: Training Image Retrieval with a Listwise Loss](https://mlsanity.com/paper/1906.07589/) (2019)
- [Self-supervising Fine-grained Region Similarities for Large-scale Image Localization](https://mlsanity.com/paper/2006.03926/) (2020)
- [CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples](https://mlsanity.com/paper/1604.02426/) (2016)
- [Detect-to-Retrieve: Efficient Regional Aggregation for Image Search](https://mlsanity.com/paper/1812.01584/) (2018)
- [Online Hyper-parameter Learning for Auto-Augmentation Strategy](https://mlsanity.com/paper/1905.07373/) (2019)
- [Attention-Aware Generalized Mean Pooling for Image Retrieval](https://mlsanity.com/paper/1811.00202/) (2018)
- [REMAP: Multi-layer entropy-guided pooling of dense CNN features for image retrieval](https://mlsanity.com/paper/1906.06626/) (2019)
- [A Dense-Depth Representation for VLAD descriptors in Content-Based Image Retrieval](https://mlsanity.com/paper/1808.05022/) (2018)

## Built on by (most cited first, 2 of 2)

- [SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place Recognition](https://mlsanity.com/paper/2509.25723/) (2025)
- [C-DIRA: Computationally Efficient Dynamic ROI Routing and Domain-Invariant Adversarial Learning for Lightweight Driver Behavior Recognition](https://mlsanity.com/paper/2512.08647/) (2025)

## Abstract (arXiv)

Image retrieval methods for place recognition learn global image descriptors that are used for fetching geo-tagged images at inference time. Recent works have suggested employing weak and self-supervision for mining hard positives and hard negatives in order to improve localization accuracy and robustness to visibility changes (e.g. in illumination or view point). However, generating hard positives, which is essential for obtaining robustness, is still limited to hard-coded or global augmentations. In this work we propose an adversarial method to guide the creation of hard positives for training image retrieval networks. Our method learns local and global augmentation policies which will increase the training loss, while the image retrieval network is forced to learn more powerful features for discriminating increasingly difficult examples. This approach allows the image retrieval network to generalize beyond the hard examples presented in the data and learn features that are robust to a wide range of variations. Our method achieves state-of-the-art recalls on the Pitts250 and Tokyo 24/7 benchmarks and outperforms recent image retrieval methods on the rOxford and rParis datasets by a noticeable margin.