paper-with-me

Papers

Dark Model Adaptation: Semantic Image Segmentation from Daytime to Nighttime

2018-10-05 · Dengxin Dai, Luc van Gool

This work addresses the problem of semantic image segmentation of nighttime scenes. Although considerable progress has been made in semantic image segmentation, it is mainly related to daytime scenarios. This paper proposes a novel method to progressive adapt the semantic models trained on daytime scenes, along with large-scale annotations therein, to nighttime scenes via the bridge of twilight time -- the time between dawn and sunrise, or between sunset and dusk. The goal of the method is to alleviate the cost of human annotation for nighttime images by transferring knowledge from standard daytime conditions. In addition to the method, a new dataset of road scenes is compiled; it consists of 35,000 images ranging from daytime to twilight time and to nighttime. Also, a subset of the nighttime images are densely annotated for method evaluation. Our experiments show that our method is effective for model adaptation from daytime scenes to nighttime scenes, without using extra human annotation.

📄 PDF Abstract BibTeX arXiv:1810.02575

Code (0)

등록된 구현이 없습니다.

Tasks

Image SegmentationSegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentation

2020-05-28 · Christos Sakaridis, Dengxin Dai, Luc van Gool

We address the problem of semantic nighttime image segmentation and improve the state-of-the-art, by adapting daytime models to nighttime without using nighttime annotations. Moreover, we design a new evaluation framewor…

Domain AdaptationImage SegmentationSegmentationSemantic Segmentation

DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation

2021-04-22 · CVPR 2021 1 · Xinyi Wu, Zhenyao Wu, Hao Guo, Lili Ju 외

Semantic segmentation of nighttime images plays an equally important role as that of daytime images in autonomous driving, but the former is much more challenging due to poor illuminations and arduous human annotations. …

Autonomous DrivingDomain AdaptationSegmentationSemantic Segmentation

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

2019-01-17 · ICCV 2019 10 · Christos Sakaridis, Dengxin Dai, Luc van Gool

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…

Image SegmentationSegmentationSemantic SegmentationStyle Transfer

Cross-Domain Correlation Distillation for Unsupervised Domain Adaptation in Nighttime Semantic Segmentation

2022-05-02 · CVPR 2022 1 · Huan Gao, Jichang Guo, Guoli Wang, Qian Zhang

The performance of nighttime semantic segmentation is restricted by the poor illumination and a lack of pixel-wise annotation, which severely limit its application in autonomous driving. Existing works, e.g., using the t…

Autonomous DrivingDomain AdaptationSemantic SegmentationUnsupervised Domain Adaptation

Mutual-GAN: Towards Unsupervised Cross-Weather Adaptation with Mutual Information Constraint

2021-06-30 · Jiawei Chen, Yuexiang Li, Kai Ma, Yefeng Zheng

Convolutional neural network (CNN) have proven its success for semantic segmentation, which is a core task of emerging industrial applications such as autonomous driving. However, most progress in semantic segmentation o…

Autonomous DrivingGenerative Adversarial NetworkImage-to-Image TranslationSegmentation+3