AI Paper Atlas

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

Adapting Vehicle Detectors for Aerial Imagery to Unseen Domains with Weak Supervision

Xiao Fang, Minhyek Jeon, Zheyang Qin, Stanislav Panev, Celso De Melo, Shuowen Hu, Shayok Chakraborty, Fernando De La Torre

ICCV 2025 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 1 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
stack car, foreground-token and background-token cross-attention maps instead of car map only (ablation)labeling with YOLOv5 · LINZ->UGRCAP50: 62.1 -> 68.8Improved
stack car, foreground-token and background-token cross-attention maps instead of car map only (ablation)labeling with YOLOv8 · LINZ->UGRCAP50: 69.8 -> 75.4Improved
stack multi-channel attention maps instead of car map only (ablation)labeling with YOLOv5 · DOTA->UGRCAP50: 68.0 -> 68.5No clear effect
stack multi-channel attention maps instead of car map only (ablation)labeling with YOLOv8 · DOTA->UGRCAP50: 74.5 -> 75.7Improved
add background token map to car + foreground token maps (ablation)stacked attention maps (YOLOv5) · LINZ->UGRCAP50: 63.7 -> 68.8Improved
add foreground token map to car + background token maps (ablation)stacked attention maps (YOLOv5) · LINZ->UGRCAP50: 65.5 -> 68.8Improved
add background token map to car + foreground token maps (ablation)stacked attention maps (YOLOv8) · LINZ->UGRCAP50: 69.1 -> 75.4Improved
add foreground token map to car + background token maps (ablation)stacked attention maps (YOLOv8) · LINZ->UGRCAP50: 73.1 -> 75.4Improved
fine-tune SD in two stages (tokens fixed in stage two) instead of one stage (ablation)Stable Diffusion tokens and U-Net · LINZ->UGRCAP50: 8.5% lower AP50 with one stageImproved
use classifier refinement instead of fixed confidence thresholds 0.3-0.7 (ablation)pseudo-label filtering (YOLOv8) · UGRCAP50No clear effect
use proposed pipeline instead of best unsupervised domain adaptation methodFaster R-CNN based detection · LINZ->UGRC and DOTA->UGRCAP50: 20.1% and 33.1%Improved
use proposed pipeline instead of best weakly supervised methodFaster R-CNN based detection · LINZ->UGRC and DOTA->UGRCAP50: 6.2% and 7.2%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