AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Large-Scale Image Geo-Localization Using Dominant Sets

Eyasu Zemene, Yonatan Tariku Tesfaye, Haroon Idrees, Andrea Prati, Marcello Pelillo, Mubarak Shah

TPAMI 2018 · Image generation › Autoregressive and latent generation · approach: Retrieval and matching with generative features · 49 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 constrained dominant set post-processing (ablation)NetVLAD · 102k Google street view imagesrank-1 accuracy (%): 49.2 -> 51.60Improved
add constrained dominant set post-processing (ablation)NetVLAD* · 102k Google street view imagesrank-1 accuracy (%): 56.00 -> 58.05Improved
add constrained dominant set post-processing (ablation)RMAC · 102k Google street view imagesrank-1 accuracy (%): 35.16 -> 40.18Improved
add constrained dominant set post-processing (ablation)MAC · 102k Google street view imagesrank-1 accuracy (%): 29.00 -> 36.30Improved
add constrained dominant set post-processing (ablation)NetVLAD · WorldCitiesrank-1 accuracy (%): 50.00 -> 53.04Improved
add constrained dominant set post-processing (ablation)NetVLAD* · WorldCitiesrank-1 accuracy (%): 50.61 -> 52.23Improved
add constrained dominant set post-processing (ablation)RMAC · WorldCitiesrank-1 accuracy (%): 29.96 -> 33.16Improved
add constrained dominant set post-processing (ablation)MAC · WorldCitiesrank-1 accuracy (%): 22.87 -> 26.31Improved
add constrained dominant set post-processing to the voting baseline (ablation)dominant set geo-localization · 102k Google street view imageslocalization within error threshold: about 10% -> about 20% improvement over state of the artImproved
add constrained dominant set post-processing to the voting baseline (ablation)dominant set geo-localization · WorldCitieslocalization within error threshold: around 2% -> 7% improvementImproved
use dominant-set feature matching instead of GMCP as the number of nearest neighbors grows (ablation)feature matching · 102k Google street view imagesaccuracy within 30 mImproved
fuse all global features (fine-tuned NetVLAD, CNN7, CNN6, GIST, HSV) with dynamic weights instead of single features (ablation)post-processing · test setlocalization accuracyImproved

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