English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Automatic post-disaster damage detection using aerial imagery is crucial forquick assessment of damage caused by disaster and development of a recoveryplan. The main problem preventing us from creating an applicable model inpractice is that damaged (positive) examples we are trying to detect are muchharder to obtain than undamaged (negative) examples, especially in short time.In this paper, we revisit the classical bootstrap aggregating approach in thecontext of modern transfer learning for data-efficient disaster damagedetection. Unlike previous classical ensemble learning articles, our workpoints out the effectiveness of simple bagging in deep transfer learning thathas been underestimated in the context of imbalanced classification. Benchmarkresults on the AIST Building Change Detection dataset show that our approachsignificantly outperforms existing methodologies, including the recentlyproposed disentanglement learning.

Revisiting Classical Bagging with Modern Transfer Learning for On-the-fly Disaster Damage Detector