AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Robust and Decomposable Average Precision for Image Retrieval

Elias Ramzi, Nicolas THOME, Clément Rambour, Nicolas Audebert, Xavier Bitot

NeurIPS 2021 · Learning theory and algorithms › Prediction and decision losses · approach: Ranking-based loss optimization · 8 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
Replace SmoothAP with ROADMAPResNet-50 image retrieval · CUB-200-2011mAP@R: 23.9 -> 25.3Improved
Replace SmoothAP with ROADMAPResNet-50 image retrieval · SOPmAP@R: 54.6 -> 56.5Improved
Replace SmoothAP with ROADMAPResNet-50 image retrieval · INaturalist-2018mAP@R: 20.7 -> 25.1Improved
Replace XBM with ROADMAPResNet-50 image retrieval · SOPR@1: 80.6 -> 82.0Improved
Replace XBM with ROADMAPResNet-50 image retrieval · INaturalist-2018mAP@R: 18.5 -> 25.1Improved
Add the H− robust rank approximation, using SupAP instead of SmoothAP (ablation)ResNet-50 image retrieval · CUB-200-2011mAP@R: 23.9 -> 24.6Improved
Add the H− robust rank approximation, using SupAP instead of SmoothAP (ablation)ResNet-50 image retrieval · SOPmAP@R: 54.6 -> 55.3Improved
Add the H− robust rank approximation, using SupAP instead of SmoothAP (ablation)ResNet-50 image retrieval · INaturalist-2018mAP@R: 20.7 -> 21.3Improved
Add calibration loss to SupAP (ablation)ResNet-50 image retrieval · CUB-200-2011mAP@R: 24.6 -> 25.3Improved
Add calibration loss to SupAP (ablation)ResNet-50 image retrieval · SOPmAP@R: 55.3 -> 56.5Improved
Add calibration loss to SupAP (ablation)ResNet-50 image retrieval · INaturalist-2018mAP@R: 21.3 -> 25.1Improved
Add calibration loss to SupAP (ablation)ResNet-50 image retrieval with batch size 32 · INaturalist-2018mAP@R: 17.13 -> 20.43Improved

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