Launch of ACDC Website

April 30th, 2021|

ACDC is a new large-​scale driving dataset for training and testing semantic segmentation algorithms on adverse visual conditions, such as fog, nighttime, rain, and snow. The dataset and associated benchmarks are published at ICCV 2021 and are now publicly available at https://acdc.vision.ee.ethz.ch.

The dataset consists […]


  • 31/10/2021:

    Dr. Dai joined the ELLIS society as a member.

  • 16/10/2021:

    We successfully organized the DeepMTL workshop at ICCV’21.

  • 28/09/2021:

    Dr. Dai will be Area Chair for CVPR’22.

  • 27/07/2021:

    Six papers have been accepted to ICCV 2021.

  • 28/06/2021:

    We just released the ACDC Dataset

Scientific Mission

The scientific mission of VAS is to develop robust and scalable perception systems for real-world applications. We focus on deep learning-based perception for autonomous systems such as autonomous driving. We are especially fascinated about scaling existing visual perception models to novel domains (e.g. adverse weather/lighting conditions, low-quality data),  to more data modality (e.g. LiDAR, Radar, Events, Audio, HD Maps), to unseen classes (e.g. rare classes), and to new tasks. The relevant research topics are summarised in the diagram shown on the right.


Go to Top