AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Deep Image Retrieval: Learning Global Representations for Image Search

Albert Gordo, Jon Almazán, Jerome Revaud, Diane Larlus

ECCV 2016 · Image generation › Autoregressive and latent generation · approach: Retrieval and matching with generative features · 794 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
fine-tune with ranking loss (R-Clean) instead of classification (C-Clean) (ablation)R-MAC VGG16 rigid grid · Oxford 5kmAP: 75.2 -> 81.1Improved
fine-tune with ranking loss (R-Clean) instead of classification (C-Clean) (ablation)R-MAC VGG16 rigid grid · Paris 6kmAP: 83.2 -> 86.0Improved
fine-tune for classification on Landmarks (ablation)R-MAC VGG16 · Oxford 5kmAP: 66.2 -> 74.8Improved
clean the Landmarks dataset for classification fine-tuning (ablation)C-Full · Oxford 5kmAP: 74.8 -> 75.2No clear effect
clean the Landmarks dataset for classification fine-tuning (ablation)C-Full · Paris 6kmAP: 82.5 -> 83.2No clear effect
train ranking network on clean data (triplet loss intolerant to outliers) (ablation)R-MAC ranking · Oxford 5kmAPImproved
initialize ranking training from a C-Full classification model (ablation)R-MAC ranking · Oxford 5kmAPImproved
learn PCA on Landmarks instead of Paris/Oxford (ablation)R-MAC reimplementation · Oxford 5kmAP: 66.9 -> 66.2Hurt
replace rigid grid with 256 RPN proposals (ablation)R-Clean · Oxford 5kmAP: 81.1 -> 83.1Improved
replace rigid grid with 256 RPN proposals (ablation)R-Clean · Paris 6kmAP: 86.0 -> 87.1Improved
replace rigid grid with 256 RPN proposals (ablation)C-Full · Oxford 5kmAP: 74.8 -> 76.8Improved
use only 16 proposals instead of rigid grid (ablation)R-Clean · Paris 6kmAP: 86.0 -> 85.4Hurt

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