AI Paper Atlas

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

Master of All: Simultaneous Generalization of Urban-Scene Segmentation to All Adverse Weather Conditions

Nikhil Reddy, Abhinav Singhal, Abhishek Kumar, Mahsa Baktashmotlagh, Chetan Arora

ECCV 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized segmentation · 18 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 class imbalance re-weighting to the loss (ablation)MALL-domain (DeepLabv3+ MobileNet) · Nighttime Driving testmIoU: 37.4 -> 38.4Improved
add sample importance weighting to the loss (ablation)MALL-domain (DeepLabv3+ MobileNet) · Nighttime Driving testmIoU: 36.1 -> 38.4Improved
add class imbalance re-weighting to the loss (ablation)MALL-domain (DeepLabv3+ MobileNet) · Dark Zurich valmIoU: 20.6 -> 21.7Improved
add sample importance weighting to the loss (ablation)MALL-domain (DeepLabv3+ MobileNet) · Dark Zurich valmIoU: 19.2 -> 21.7Improved
use MALL-sample instead of TENTDeepLabv3+ MobileNet · Nighttime Driving testmIoU: 33.3 -> 36.8Improved
use per-domain adaptation (MALL-domain) instead of per-sampleDeepLabv3+ MobileNet · Nighttime Driving testmIoU: 36.8 -> 38.4Improved
adapt with MALL-domain on nighttime drivingDeepLabv3+ ResNet101 · Cityscapes daymIoU: 78.5 -> 75.7Hurt
adapt with MALL-domain on nighttime drivingDeepLabv3+ MobileNet · Cityscapes daymIoU: 61.6 -> 59.6Hurt
apply MALL-domain at test timeMobileNetV2 · Average adverse-condition mIoUmIoU: 24.2 -> 38.6Improved
apply MALL-domain at test timeSegFormer-B0 · Average adverse-condition mIoUmIoU: 37.3 -> 38.7Improved
apply MALL-domain at test timeRobustNet-ResNet101 · Average adverse-condition mIoUmIoU: 38.8 -> 42.0Improved
apply MALL-domain at test timeIBNNet · Average adverse-condition mIoUmIoU: 39.6 -> 41.3Improved

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