# Guided Curriculum Model Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation

arXiv: https://arxiv.org/abs/1901.05946 · HTML: https://mlsanity.com/paper/1901.05946/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jan 2019.

## Built on by (most cited first, 4 of 4)

- [ScatterNeRF: Seeing Through Fog with Physically-Based Inverse Neural Rendering](https://mlsanity.com/paper/2305.02103/) (2023)
- [FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentation](https://mlsanity.com/paper/2503.17940/) (2025)
- [DTBS: Dual-Teacher Bi-directional Self-training for Domain Adaptation in Nighttime Semantic Segmentation](https://mlsanity.com/paper/2401.01066/) (2024)
- [Show or Tell? Effectively prompting Vision-Language Models for semantic segmentation](https://mlsanity.com/paper/2503.19647/) (2025)

## Abstract (arXiv)

Most progress in semantic segmentation reports on daytime images taken under favorable illumination conditions. We instead address the problem of semantic segmentation of nighttime images and improve the state-of-the-art, by adapting daytime models to nighttime without using nighttime annotations. Moreover, we design a new evaluation framework to address the substantial uncertainty of semantics in nighttime images. Our central contributions are: 1) a curriculum framework to gradually adapt semantic segmentation models from day to night via labeled synthetic images and unlabeled real images, both for progressively darker times of day, which exploits cross-time-of-day correspondences for the real images to guide the inference of their labels; 2) a novel uncertainty-aware annotation and evaluation framework and metric for semantic segmentation, designed for adverse conditions and including image regions beyond human recognition capability in the evaluation in a principled fashion; 3) the Dark Zurich dataset, which comprises 2416 unlabeled nighttime and 2920 unlabeled twilight images with correspondences to their daytime counterparts plus a set of 151 nighttime images with fine pixel-level annotations created with our protocol, which serves as a first benchmark to perform our novel evaluation. Experiments show that our guided curriculum adaptation significantly outperforms state-of-the-art methods on real nighttime sets both for standard metrics and our uncertainty-aware metric. Furthermore, our uncertainty-aware evaluation reveals that selective invalidation of predictions can lead to better results on data with ambiguous content such as our nighttime benchmark and profit safety-oriented applications which involve invalid inputs.