AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

End-to-End Learning of Deep Visual Representations for Image Retrieval

Albert Gordo, Jon Almazán, Jérôme Revaud, Diane Larlus

IJCV 2017 · Vision-language and multimodal › Human and embodied modeling · approach: Composed and text-based image retrieval · 547 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
finetune with ranking loss after classification warm-up (vs ImageNet weights) (ablation)R-MAC ResNet101 · Oxford 5kmAP: 69.4 -> 84.1Improved
use ranking loss instead of classification loss (ablation)R-MAC VGG16 · Oxford 5kmAP: 74.2 -> 79.9Improved
warm up with classification finetuning before ranking (ablation)R-MAC VGG16 · Oxford 5kmAP: 76.3 -> 79.9Improved
warm up with classification finetuning before ranking (ablation)R-MAC ResNet101 · Oxford 5kmAP: 83.4 -> 84.1Improved
train ranking on cleaned landmarks instead of full (ablation)R-MAC · Oxford/Paris/HolidaysmAPImproved
finetune with classification loss on clean instead of full landmarks (ablation)R-MAC ResNet101 · Oxford 5kmAP: 77.7 -> 78.5No clear effect
finetune for retrieval (ablation)R-MAC ResNet101 · UKBrecall@4: 3.89 -> 3.83Hurt
replace rigid grid by 256 region proposals (ablation)R-MAC VGG16 ImageNet · Oxford 5kmAP: 60.3 -> 65.4Improved
replace rigid grid by 256 region proposals (ablation)R-MAC ResNet101 finetuned · Oxford 5kmAP: 84.1 -> 85.2Improved
replace rigid grid by 20 region proposals (ablation)R-MAC ResNet101 finetuned · HolidaysmAP: 94.0 -> 92.0Hurt
add multi-resolution on query side (ablation)Ft ResNet101 · Oxford 5kmAP: 84.1 -> 84.9Improved
add multi-resolution on database side (ablation)Ft ResNet101 · Oxford 5kmAP: 84.1 -> 85.2Improved

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