AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Revisiting IM2GPS in the Deep Learning Era

Nam Vo, Nathan Jacobs, James Hays

ICCV 2017 · Image generation › Autoregressive and latent generation · approach: Retrieval and matching with generative features · 142 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
use kNN kernel density retrieval instead of fine-grained classificationVGG-16 [L] 7011C · Im2GPS test setaccuracy within 1km: 6.8 -> 12.2Improved
use kNN retrieval (sigma=4) instead of PlaNet-style classification at continent levelVGG-16 [L] · Im2GPS test setaccuracy within 2500km: 71.3 -> 71.3No clear effect
replace nearest neighbour with kNN density estimation (sigma=1) (ablation)[L] retrieval, Im2GPS database · Im2GPS test setaccuracy within 1km: 12.7 -> 13.1Improved
increase kernel bandwidth sigma from 4 to 16 (ablation)[L] kNN, Im2GPS database · Im2GPS test setaccuracy within 1km: 12.2 -> 10.6Hurt
increase kernel bandwidth sigma from 4 to 16 (ablation)[L] kNN, Im2GPS database · Im2GPS test setaccuracy within 2500km: 71.3 -> 75.9Improved
enlarge reference database from Im2GPS 6M to 28M images (ablation)[L] kNN sigma=4 · Im2GPS test setaccuracy within 1km: 12.2 -> 14.4Improved
enlarge reference database from Im2GPS 6M to 28M images (ablation)[L] kNN sigma=4 · Im2GPS test setaccuracy within 2500km: 71.3 -> 73.4Improved
replace Im2GPS database with YFCC22m database only (ablation)[L] NN · Im2GPS test setaccuracy within 1km: 12.7 -> 12.2Hurt
add DML triplet ranking fine-tuning to the classification network (ablation)VGG-16 [L] · Im2GPS3k and YFCC4kgeolocalization accuracyNo clear effect
add multiple classification losses (six partitions, model M) instead of single 7011-way loss (ablation)VGG-16 [L] · Im2GPS3k and YFCC4kgeolocalization accuracyMixed
use finer partitioning of the Earth (7011 vs 80 or 359 classes) (ablation)classification · Im2GPS3k and YFCC4kaccuracy at coarse and fine thresholdsMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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