Research map / Detection and segmentation / Open-set and few-shot detection
ACDC: The Adverse Conditions Dataset With Correspondences for Semantic Driving Scene Understanding
Christos Sakaridis, Dengxin Dai, Luc Van Gool
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 changed | Where | Measured | Effect |
|---|---|---|---|
| apply FDA pixel-level adaptation instead of no adaptation | DeepLabv2 · Cityscapes->ACDC UDA | mIoU (%): 38.0 -> 45.7 | Improved |
| apply AdaptSegNet adaptation | DeepLabv2 · Cityscapes->ACDC UDA | mIoU (%): 38.0 -> 33.4 | Hurt |
| apply ADVENT adaptation | DeepLabv2 · Cityscapes->ACDC UDA | mIoU (%): 38.0 -> 32.7 | Hurt |
| add weak supervision from adverse-normal correspondences (MGCDA) | RefineNet · Cityscapes->ACDC | mIoU (%): 43.7 -> 48.7 | Improved |
| use 1600 target labels instead of 100 | DeepLabv2 oracle · ACDC | mIoU (%): 47.1 -> 55.3 | Improved |
| train jointly on all conditions rather than condition experts (ablation) | HRNet · ACDC All | mIoU (%): 70.9 -> 75.0 | Improved |
| train jointly on all conditions rather than condition experts (ablation) | DeepLabv3+ · ACDC All | mIoU (%): 69.6 -> 70.0 | Improved |
| add ACDC to Cityscapes training | HRNet · Cityscapes val | mIoU (%): 80.4 -> 81.2 | Improved |
| add Cityscapes to ACDC training | HRNet · ACDC test | mIoU (%): 75.0 -> 74.8 | No clear effect |
| use max-softmax as confidence instead of constant | DeepLabv3+ · ACDC All | AUIoU (%): 70.0 -> 67.8 | Hurt |
| use ground-truth invalid mask as confidence | DeepLabv3+ · ACDC All | AUIoU (%): 70.0 -> 73.3 | Improved |
| use learned confidence of prior outlier method instead of constant | prior uncertainty method · ACDC test | AUIoU (%): 53.0 -> 52.0 | Hurt |
Closest papers by meaning
- ACDC: The Adverse Conditions Dataset With Correspondences for Robust Semantic Driving Scene Perception (TPAMI 2025 · similarity 0.97)
- MUSES: The Multi-Sensor Semantic Perception Dataset for Driving under Uncertainty (ECCV 2024 · similarity 0.87)
- Cross-Dataset Collaborative Learning for Semantic Segmentation in Autonomous Driving (AAAI 2022 · similarity 0.86)
- A Dataset for Semantic Segmentation in the Presence of Unknowns (CVPR 2025 · similarity 0.84)
- Weakly Supervised Semantic Segmentation for Driving Scenes (AAAI 2024 · similarity 0.84)
- Spotting the Unexpected (STU): A 3D LiDAR Dataset for Anomaly Segmentation in Autonomous Driving (CVPR 2025 · similarity 0.84)
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.
