cs.CVNov 18, 2026

ShadowTransfer: A Geographic Transfer Benchmark for Overhead Shadow Detection

Authors: Shagun Mittal, Raymond A. Yeh, Satish Ukkusuri

Abstract

Overhead aerial imagery feeds dense-prediction pipelines that are routinely trained in one geographic region and deployed in another, yet no benchmark measures how shadow detection models transfer across regions. Existing overhead shadow datasets either lack a geographic transfer protocol or rely on automatically generated labels. We introduce ShadowTransfer, a benchmark of 4,500 human-verified shadow masks across three U.S. cities at two native resolutions, paired with a leave-one-city-out evaluation protocol. Under vanilla training, holding out the test city costs 3.5 to 7.8 mIoU across four architectures, the gap remains significant when the training set grows from 225 to 900 images, and six of eight adaptation methods degrade more than vanilla training on average. We propose a three-probe framework that diagnoses where and how the transfer breaks: the failure operates in feature space, beyond the reach of pixel-histogram matching, shows up as a confidence collapse on shadow pixels while background confidence stays intact, and is recoverable by retraining different architectural components depending on the model: encoder for some, decoder for others. These findings replicate on INRIA building footprints, suggesting they describe geographic transfer beyond shadows. Guided by the diagnosis, we build Spectral Information Bottleneck (SIB), a plug-in module with one component per finding. Across the 9 (architecture, held-out city) cells, SIB has the smallest mean gap to the within-city upper bound of the ten methods we evaluate (6.42 mIoU), level with FDA. The benchmark, LOCO protocol, code, and trained models are released to support reproducible evaluation of geographic transfer in overhead dense prediction.

Figures & tables

Appendix figures & tables47 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Revisiting Shadow Detection from a Vision-Language Perspective

    May 12, 2026Yonghui Wang, Shaokai Liu, Wengang Zhou +2Vision-Language Models

  2. deSEO: Physics-Aware Dataset Creation for High-Resolution Satellite Image Shadow Removal

    May 5, 2026Lorenzo Beltrame, Jules Salzinger, Filip Svoboda +4Remote Sensing Image UnderstandingShadow Removal

  3. After a Decade: Bringing Shadow Removal into the Real World with Agentic Training Data

    Sep 29, 2026Shilin Hu, Jingyi Xu, Dimitris Samaras +1Synthetic Data AugmentationShadow Removal