AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

CMDA: Cross-Modality Domain Adaptation for Nighttime Semantic Segmentation

Ruihao Xia, Chaoqiang Zhao, Meng Zheng, Ziyan Wu, Qiyu Sun, Yang Tang

ICCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized segmentation · 55 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
add event modality at training time and fuse image+event at testCMDA · DSEC Night-SemanticmIoU: 56.0 -> 60.1 vs DAFormerImproved
train with events but test with images onlyCMDA · DSEC Night-SemanticmIoU: 55.1 -> 57.8Improved
add Image Content-Extractor (ablation)DAFormer baseline · DSEC Night-SemanticMIoU(I): 55.06 -> 56.78Improved
add events via Image Motion-Extractor alone, without random fusion with I_CE (ablation)DAFormer baseline · DSEC Night-SemanticMIoU(I): 55.06 -> 53.46Hurt
combine I_CE and E_ME with random fusion (ablation)CMDA · DSEC Night-SemanticMIoU(I+E): 55.65 -> 60.05Improved
add day-to-night style transfer network (MGCDA) (ablation)DAFormer baseline · Dark ZurichmIoU: 53.5 -> 50.2Hurt
add Image Content-Extractor instead of style transferDAFormer baseline · Dark ZurichmIoU: 53.5 -> 54.8Improved
use Image Motion-Extractor events instead of ESIM events (ablation)CMDA · DSEC Night-SemanticMIoU(E): 42.09 -> 44.91Improved
add event style transfer network G to E_ME (ablation)CMDA · DSEC Night-SemanticMIoU(I+E): 56.63 -> 60.05Improved
increase shift gamma from 1 to 4 (ablation)Image Content-Extractor · DSEC Night-SemanticMIoU(I+E): 60.05 -> 58.57Hurt
set beta to 0.03 rather than 0.005 (ablation)Image Content-Extractor · DSEC Night-SemanticMIoU(I+E): 60.05 -> 57.61Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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