AI Paper Atlas

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

Keep Your Friends Close, and the Right Neighbours Closer: Disaster-Conditioned Kernel-Regularized Graph Attention for Building Damage Classification

Fuad Hasan, Chul Min Yeum

ECCV 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Zero-shot robustness and transfer · 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
add graph attention over neighbouring buildings (vanilla GAT)patch-only encoder · xBD LOEOMacro-F1: 0.433 -> 0.453Improved
add graph attention (vanilla GAT)patch-only encoder · xBD LOEOResidual Moran's I: 0.248 -> 0.256No clear effect
add DCMS kernel prior (ablation)vanilla GAT · xBD LOEOMacro-F1: 0.453 -> 0.473Improved
add DCMS kernel prior (ablation)vanilla GAT · xBD LOEOResidual Moran's I: 0.256 -> 0.182Improved
add disaster-type conditioning (ablation)vanilla GAT · xBD LOEOMacro-F1: 0.453 -> 0.460Improved
add residual Moran de-correlation loss (ablation)vanilla GAT · xBD LOEOResidual Moran's I: 0.256 -> 0.139Improved
add residual Moran de-correlation loss (ablation)vanilla GAT · xBD LOEOMacro-F1: 0.453 -> 0.450No clear effect
add disaster conditioning on top of kernel + residual (ablation)kernel + residual model · xBD LOEOMacro-F1: 0.490 -> 0.503Improved
add residual loss on top of kernel + disaster conditioning (ablation)kernel + disaster model · xBD LOEOResidual Moran's I: 0.116 -> 0.079Improved
use pre+post bitemporal input instead of post-only (ablation)Ours · xView2 holdout (fixed instances)Macro-F1: 0.828 -> 0.873Improved
vary kNN k from 8 to 16 to 32 (ablation)Ours · xBD LOEOMacro-F1: 0.498, 0.503, 0.500No clear effect
apply Ours vs patch-only to unseen datasetOurs · xBD to Ida-BDMacro-F1: 0.275 -> 0.335Improved

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