Leveraging Contrastive Learning for Semantic Segmentation with Consistent Labels Across Varying Appearances

TL;DR

This paper presents a synthetic urban scene dataset and a domain adaptation method that enforces feature consistency across weather variations, improving segmentation performance in diverse conditions.

Contribution

It introduces a new synthetic dataset capturing weather variations and a domain adaptation approach leveraging multi-weather scene consistency.

Findings

Improved segmentation performance across weather conditions

Enhanced feature alignment metrics

Effective synthetic data generation strategies

Abstract

This paper introduces a novel synthetic dataset that captures urban scenes under a variety of weather conditions, providing pixel-perfect, ground-truth-aligned images to facilitate effective feature alignment across domains. Additionally, we propose a method for domain adaptation and generalization that takes advantage of the multiple versions of each scene, enforcing feature consistency across different weather scenarios. Our experimental results demonstrate the impact of our dataset in improving performance across several alignment metrics, addressing key challenges in domain adaptation and generalization for segmentation tasks. This research also explores critical aspects of synthetic data generation, such as optimizing the balance between the volume and variability of generated images to enhance segmentation performance. Ultimately, this work sets forth a new paradigm for synthetic data generation and domain adaptation.