AI Paper Atlas

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

Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understanding

Christos Sakaridis, Dengxin Dai, Simon Hecker, Luc Van Gool

ECCV 2018 · Detection and segmentation › Open-set and few-shot detection · approach: Remote sensing segmentation and change · 279 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
fine-tune on lighter synthetic fog (beta=0.005) instead of denser (beta=0.01), Stereo-DBF (ablation)RefineNet · Foggy Zurich-testmIoU all classes: 31.2 -> 33.4Improved
fine-tune on lighter synthetic fog (beta=0.005) instead of denser, Stereo-GF (ablation)RefineNet · Foggy Zurich-testmIoU all classes: 30.2 -> 33.9Improved
fine-tune on light Stereo-GF synthetic fog vs clear-weather modelRefineNet · Foggy Zurich-testmIoU all classes: 32.0 -> 33.9Improved
fine-tune on dense Stereo-GF synthetic fog (beta=0.01) vs clear-weather modelRefineNet · Foggy Zurich-testmIoU all classes: 32.0 -> 30.2Hurt
use semantic-aware Stereo-DBF instead of Stereo-GF for dense synthetic fog (beta=0.01) (ablation)RefineNet · Foggy Zurich-testmIoU all classes: 30.2 -> 31.2Improved
use Stereo-DBF instead of Stereo-GF at beta=0.005 (ablation)RefineNet · Foggy Zurich-testmIoU all classes: 33.9 -> 33.4No clear effect
use Stereo-DBF instead of Stereo-GF at beta=0.005 (ablation)RefineNet · Foggy Driving-densemIoU all classes: 32.5 -> 32.8Improved
add second CMAda step (dense synthetic fog plus light real fog) after step 1, Stereo-DBF (ablation)RefineNet · Foggy Zurich-testmIoU all classes: 33.4 -> 37.9Improved
add second CMAda step after step 1, Stereo-GF (ablation)RefineNet · Foggy Zurich-testmIoU all classes: 33.9 -> 34.7Improved
add second CMAda step after step 1, Stereo-DBF (ablation)RefineNet · Foggy Zurich-testmIoU frequent classes: 49.0 -> 56.7Improved
add second CMAda step (with real Foggy Zurich-light) after step 1, Stereo-DBF (ablation)RefineNet · Foggy Driving-densemIoU all classes: 32.8 -> 34.3Improved
full CMAda pipeline with Stereo-DBF vs clear-weather RefineNetRefineNet · Foggy Zurich-testmIoU all classes and frequent classes: +5.9% and +7.9%Improved

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