# Improving Generalization of Synthetically Trained Sonar Image Descriptors for Underwater Place Recognition

arXiv: https://arxiv.org/abs/2308.01058 · HTML: https://mlsanity.com/paper/2308.01058/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 41 references that are in the map.
- First posted on arXiv 2 Aug 2023.

## Builds on (most cited first, 9 of 9)

- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change](https://mlsanity.com/paper/2005.08135/) (2020)
- [On the Performance of ConvNet Features for Place Recognition](https://mlsanity.com/paper/1501.04158/) (2015)
- [Improved Embeddings with Easy Positive Triplet Mining](https://mlsanity.com/paper/1904.04370/) (2019)
- [Learnable pooling with Context Gating for video classification](https://mlsanity.com/paper/1706.06905/) (2017)
- [DAVE Aquatic Virtual Environment: Toward a General Underwater Robotics Simulator](https://mlsanity.com/paper/2209.02862/) (2022)
- [Deep Architectures and Ensembles for Semantic Video Classification](https://mlsanity.com/paper/1807.01026/) (2018)
- [Virtual Maps for Autonomous Exploration of Cluttered Underwater Environments](https://mlsanity.com/paper/2202.08359/) (2022)

## Built on by (most cited first, 1 of 1)

- [A Sonar-based AUV Positioning System for Underwater Environments with Low Infrastructure Density](https://mlsanity.com/paper/2405.01971/) (2024)

## Abstract (arXiv)

Autonomous navigation in underwater environments presents challenges due to factors such as light absorption and water turbidity, limiting the effectiveness of optical sensors. Sonar systems are commonly used for perception in underwater operations as they are unaffected by these limitations. Traditional computer vision algorithms are less effective when applied to sonar-generated acoustic images, while convolutional neural networks (CNNs) typically require large amounts of labeled training data that are often unavailable or difficult to acquire. To this end, we propose a novel compact deep sonar descriptor pipeline that can generalize to real scenarios while being trained exclusively on synthetic data. Our architecture is based on a ResNet18 back-end and a properly parameterized random Gaussian projection layer, whereas input sonar data is enhanced with standard ad-hoc normalization/prefiltering techniques. A customized synthetic data generation procedure is also presented. The proposed method has been evaluated extensively using both synthetic and publicly available real data, demonstrating its effectiveness compared to state-of-the-art methods.