# A Cross-Season Correspondence Dataset for Robust Semantic Segmentation

## TL;DR

This paper introduces a dataset and method for improving semantic segmentation robustness across seasons by using 2D-2D matches from images taken under different conditions, with minimal human effort.

## Contribution

It presents a novel approach to leverage cross-season correspondences for training more robust segmentation models and provides publicly available datasets for further research.

## Key findings

- Enhanced segmentation robustness across seasons
- Datasets with cross-season and day-night correspondences released
- Supervision with correspondences improves model performance

## Abstract

In this paper, we present a method to utilize 2D-2D point matches between images taken during different image conditions to train a convolutional neural network for semantic segmentation. Enforcing label consistency across the matches makes the final segmentation algorithm robust to seasonal changes. We describe how these 2D-2D matches can be generated with little human interaction by geometrically matching points from 3D models built from images. Two cross-season correspondence datasets are created providing 2D-2D matches across seasonal changes as well as from day to night. The datasets are made publicly available to facilitate further research. We show that adding the correspondences as extra supervision during training improves the segmentation performance of the convolutional neural network, making it more robust to seasonal changes and weather conditions.