ACDC: The Adverse Conditions Dataset with Correspondences for Semantic Driving Scene Understanding
Open access
Datum
2021Typ
- Conference Paper
ETH Bibliographie
yes
Altmetrics
Abstract
Level 5 autonomy for self-driving cars requires a robust visual perception system that can parse input images under any visual condition. However, existing semantic segmentation datasets are either dominated by images captured under normal conditions or are small in scale. To address this, we introduce ACDC, the Adverse Conditions Dataset with Correspondences for training and testing semantic segmentation methods on adverse visual conditions. ACDC consists of a large set of 4006 images which are equally distributed between four common adverse conditions: fog, nighttime, rain, and snow. Each adverse-condition image comes with a high-quality fine pixel-level semantic annotation, a corresponding image of the same scene taken under normal conditions, and a binary mask that distinguishes between intra-image regions of clear and uncertain semantic content. Thus, ACDC supports both standard semantic segmentation and the newly introduced uncertainty-aware
semantic segmentation. A detailed empirical study demonstrates the challenges that the adverse domains of ACDC pose to state-of-the-art supervised and unsupervised approaches and indicates the value of our dataset in steering future progress in the field. Our dataset and benchmark are publicly available. Mehr anzeigen
Persistenter Link
https://doi.org/10.3929/ethz-b-000518792Publikationsstatus
publishedExterne Links
Buchtitel
2021 IEEE/CVF International Conference on Computer Vision (ICCV)Seiten / Artikelnummer
Verlag
IEEEKonferenz
Organisationseinheit
03514 - Van Gool, Luc / Van Gool, Luc
ETH Bibliographie
yes
Altmetrics