ACDC: The Adverse Conditions Dataset with Correspondences for Robust Semantic Driving Scene Perception

TL;DR

ACDC is a large, diverse dataset designed to improve semantic perception in adverse driving conditions, supporting multiple tasks and highlighting challenges for current methods.

Contribution

We introduce ACDC, a comprehensive dataset with annotations for adverse conditions, enabling robust training and evaluation of perception models under challenging scenarios.

Findings

Adverse conditions significantly reduce the performance of state-of-the-art methods.

Uncertainty-aware semantic segmentation improves robustness in adverse scenarios.

The dataset reveals gaps in current perception approaches under adverse conditions.

Abstract

Level-5 driving automation requires a robust visual perception system that can parse input images under any condition. However, existing driving datasets for dense semantic perception 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 methods for diverse semantic perception tasks on adverse visual conditions. ACDC consists of a large set of 8012 images, half of which (4006) are equally distributed between four common adverse conditions: fog, nighttime, rain, and snow. Each adverse-condition image comes with a high-quality pixel-level panoptic annotation, a corresponding image of the same scene under normal conditions, and a binary mask that distinguishes between intra-image regions of clear and uncertain semantic content. 1503 of the corresponding normal-condition images feature panoptic annotations, raising the total annotated images to 5509. ACDC supports the standard tasks of semantic segmentation, object detection, instance segmentation, and panoptic segmentation, as well as 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 at https://acdc.vision.ee.ethz.ch