AI Paper Atlas

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

DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation

Zuxuan Wu, Xintong Han, Yen-Liang Lin, Mustafa Gokhan Uzunbas, Tom Goldstein, Ser Nam Lim, Larry S. Davis

ECCV 2018 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized segmentation · 252 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 channel-wise feature alignment in the segmentation network (ablation)CycleGAN images · Synthia->CityscapesmIoU: 30.4 -> 31.7Improved
add channel-wise feature alignment in the segmentation network (ablation)UNIT images · Synthia->CityscapesmIoU: 31.6 -> 32.7Improved
add channel-wise feature alignment in the segmentation network (ablation)DCAN · Synthia->CityscapesmIoU: 33.8 -> 35.4Improved
train image generator and segmentation network end-to-end instead of two stages (ablation)DCAN · Synthia->CityscapesmIoU: 33.7 -> 35.4Improved
use DCAN channel-wise image synthesis instead of CycleGAN (ablation)FCN8s-VGG16 · Synthia->CityscapesmIoU: 30.4 -> 33.8Improved
use channel-wise alignment instead of adversarial ADDA (ablation)FCN8s-VGG16 · Synthia->CityscapesmIoU: 34.0 -> 35.4Improved
align features after Conv3 rather than Conv7 (ablation)DCAN FCN8s-VGG16 · Synthia->CityscapesmIoU: 32.7 -> 35.4Improved
align features after Conv3 rather than Conv6 (ablation)DCAN FCN8s-VGG16 · Synthia->CityscapesmIoU: 33.2 -> 35.4Improved
align after Conv2 instead of no alignment (ablation)DCAN FCN8s-VGG16 · Synthia->CityscapesmIoU: 33.8 -> 34.0No clear effect
align at Conv7 instead of no alignment (ablation)DCAN FCN8s-VGG16 · Synthia->CityscapesmIoU: 33.8 -> 32.7Hurt
increase input resolution from 256x512 to 512x1024 (ablation)DCAN FCN8s-VGG16 · Synthia->CityscapesmIoU: 29.6 -> 35.4Improved
add DCAN adaptation to source-only trainingPSPNet · Gta5->CityscapesmIoU: 33.3 -> 41.7Improved

Later papers that compared with this method

5 later accepted papers report DCAN as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

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