AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Similarity Min-Max: Zero-Shot Day-Night Domain Adaptation

Rundong Luo, Wenjing Wang, Wenhan Yang, Jiaying Liu

ICCV 2023 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 39 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
train D then F in two steps instead of alternating like GAN (ablation)similarity min-max pipeline · CODaN nighttime testtop-1 accuracy (%): 63.84 -> 65.87Improved
use learned exposure-guided quadratic-curve darkening instead of brightness adjustment (ablation)darkening module D · CODaN nighttime testtop-1 accuracy (%): 57.96 -> 65.87Improved
use learned darkening instead of fixed gamma correction (ablation)darkening module D · CODaN nighttime testtop-1 accuracy (%): 63.96 -> 65.87Improved
use iterative quadratic curve instead of reciprocal curve (ablation)darkening module D · CODaN nighttime testtop-1 accuracy (%): 62.60 -> 65.87Improved
use iterative quadratic curve instead of gamma curve (ablation)darkening module D · CODaN nighttime testtop-1 accuracy (%): 64.16 -> 65.87Improved
add similarity minimization loss L_D^sim (ablation)darkening module D · CODaN nighttime testtop-1 accuracy (%): 64.56 -> 65.87Improved
add similarity maximization loss L_F^sim (ablation)feature extractor F · CODaN nighttime testtop-1 accuracy (%): 64.88 -> 65.87Improved
add both similarity losses (min and max) (ablation)similarity min-max framework · CODaN nighttime testtop-1 accuracy (%): 64.08 -> 65.87Improved
add low-light enhancement as preprocessing for daytime baselineRefineNet · Nighttime DrivingmIoU (%): 34.3 -> 25.1 (RUAS)Hurt
apply the min-max framework to segmentation, place recognition and videodaytime baselines · Nighttime Driving, Dark-Zurich, Tokyo 24/7, ARIDtask accuracy: ARID 47.02 -> 51.52; Dark-Zurich 30.6 -> 40.2Improved

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