AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

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

Christos Sakaridis, Haoran Wang, Ke Li, René Zurbrügg, Arpit Jadon, Wim Abbeloos, Daniel Olmeda Reino, Luc Van Gool, Dengxin Dai

TPAMI 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation · 35 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use SegFormer backbone with MIC instead of DeepLabv2 UDAUDA segmentation · Cityscapes->ACDCmIoU: MIC 70.4 vs FDA 45.7Improved
apply DeepLabv2-based adversarial UDA (AdaptSegNet, ADVENT, BDL)DeepLabv2 source model · Cityscapes->ACDCmIoU: 38.0 -> 33.4 (AdaptSegNet), 32.7 (ADVENT)Hurt
add input-level Fourier adaptation (FDA/CISS)DeepLabv2 source model · Cityscapes->ACDCmIoU: 38.0 -> 45.7 (FDA), 47.2 (CISS)Improved
add MIC UDA to SegFormer source modelSegFormer · Cityscapes->ACDCmIoU: 56.8 -> 70.4Improved
add DAFormer UDA to SegFormer source modelSegFormer · Cityscapes->ACDCmIoU: 56.8 -> 55.4Hurt
add weak supervision via image correspondences (MGCDA)RefineNet · Cityscapes->ACDCmIoU: 43.7 -> 48.7Improved
add target-domain adaptation (CISS) on sensor-level shiftDeepLabv2 · Cityscapes->ACDC-ReferencemIoU: 51.7 -> 63.5 vs oracle 62.5Improved
add MIC adaptation on sensor-level shiftSegFormer · Cityscapes->ACDC-ReferencemIoU: 68.4 -> 77.0 vs oracle 72.4Improved
add UDA to detectors (adversarial DA-Faster, SADA)Faster R-CNN · Cityscapes->ACDCAP50 box: 20.8 -> 19.8 (DA-Faster), 19.7 (SADA)Hurt
add MIC (SADA) to Faster R-CNNFaster R-CNN · Cityscapes->ACDCAP50 box: 20.8 -> 25.9Improved
train uber model on all conditions instead of condition expert (ablation)HRNet · ACDC all conditionsmIoU: 70.9 -> 75.0Improved
train uber model on all conditions instead of fog expert (ablation)Mask R-CNN · ACDC fogAP mask: 15.6 -> 24.4Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy