CoSA: Correlation-Guided Change A ttention with Learnable Residual Gating for Remote Sensing Change Detection
Paper recorded by Signals 4 on 2026-09-08 in cs.CV. Abstract reproduced from arXiv; link to the original below.
Published 2026-09-08 on arXiv · recorded by Signals 4 on 2026-09-09
Category: cs.CV · 计算机视觉 · first seen 2026-09-09
Abstract
Pixel-level annotation of fixed traffic-camera imagery is expensive, while crosswalk models trained from street-level imagery face a substantial viewpoint and appearance shift when applied to elevated CCTV. We investigate a data-efficient target-domain pipeline using 241 manually annotated CCTV images and 5,926 unlabeled CCTV frames. A source-domain experiment trains a 31.0M-parameter custom U-Net
Read on arXiv →
Cite this page: CoSA: Correlation-Guided Change A ttention with Learnable Residual Gating for Remote Sensing Change Detection: the #124 most recent of 237 cs.CV papers we have recorded (as of 2026-09-08). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/cosa-correlation-guided-change-a-ttention-with-learnable-residual-gating-for-rem.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable:
papers.json
Get 4 AI signals a day by email — free.
Get 4 AI signals a day by email — free