# Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localization

## TL;DR

This paper introduces a self-supervised neural network, FGSN, that produces fine-grained, consistent scene segmentations across seasons, significantly enhancing long-term visual localization accuracy.

## Contribution

The novel FGSN network provides more detailed and seasonally consistent segmentations, improving robustness of localization methods over time.

## Key findings

- FGSN achieves higher segmentation detail with more labels.
- Integrating FGSN improves localization accuracy in changing environments.
- Self-supervised training enables effective learning without extensive labeled data.

## Abstract

Long-term visual localization is the problem of estimating the camera pose of a given query image in a scene whose appearance changes over time. It is an important problem in practice, for example, encountered in autonomous driving. In order to gain robustness to such changes, long-term localization approaches often use segmantic segmentations as an invariant scene representation, as the semantic meaning of each scene part should not be affected by seasonal and other changes. However, these representations are typically not very discriminative due to the limited number of available classes. In this paper, we propose a new neural network, the Fine-Grained Segmentation Network (FGSN), that can be used to provide image segmentations with a larger number of labels and can be trained in a self-supervised fashion. In addition, we show how FGSNs can be trained to output consistent labels across seasonal changes. We demonstrate through extensive experiments that integrating the fine-grained segmentations produced by our FGSNs into existing localization algorithms leads to substantial improvements in localization performance.