AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Spatial-Aware Feature Aggregation for Image based Cross-View Geo-Localization

Yujiao Shi, Liu Liu, Xin Yu, Hongdong Li

NeurIPS 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Uncertainty-aware multi-view learning · 115 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 polar transform of aerial images (ablation)VGG_gp baseline · CVUSAr@1: 39.72 -> 65.74Improved
add polar transform of aerial images (ablation)VGG_gp baseline · CVACT_valr@1: 32.22 -> 56.65Improved
add polar transform of aerial imagesCVM-NET · CVUSAr@1: 22.53 -> 50.00Improved
add polar transform of aerial imagesCVM-NET · CVACT_valr@1: 20.15 -> 34.92Improved
replace global max-pooling with single SPE module (ablation)VGG_gp · CVUSAr@1: 39.72 -> 58.79Improved
replace global max-pooling with single SPE module (ablation)VGG_gp · CVACT_valr@1: 32.22 -> 42.96Improved
increase SPE modules from 1 to 8 (ablation)SAFA · CVUSAr@1: 58.79 -> 81.15Improved
increase SPE modules from 4 to 8 (ablation)SAFA · CVACT_valr@1: 74.61 -> 78.28Improved
add polar transform to SAFA (M=8) (ablation)SAFA (M=8) · CVUSAr@1: 81.15 -> 89.84Improved
add polar transform to SAFA (M=8) (ablation)SAFA (M=8) · CVACT_valr@1: 78.28 -> 81.03Improved

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