AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Learning and Calibrating Per-Location Classifiers for Visual Place Recognition

Petr Gronát, Josef Šivic, Guillaume Obozinski, Tomáš Pajdla

IJCV 2016 · Label-efficient and robust learning › Recognition and long-tail · approach: Decoupled and calibrated long-tail training · 11 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 calibration (w-norm) to learnt per-location SVMs (ablation)BOW per-location SVM · Pittsburgh 25k (BOW)recall@1: 6.4 -> 31.8Improved
add p-val calibration to learnt per-location SVMs (ablation)BOW per-location SVM · Pittsburgh 25k (BOW)recall@1: 6.4 -> 33.0Improved
learn per-location classifiers with p-val calibrationBOW · Pittsburgh 25k (BOW)recall@1: 28.7 -> 33.0Improved
learn per-location classifiers with w-norm calibrationBOW · Pittsburgh 25k (BOW)recall@1: 28.7 -> 31.8Improved
use w-norm instead of confuser suppressionBOW · Pittsburgh 25k (BOW)recall@1: 29.6 -> 31.8Improved
use p-val instead of w-norm calibration for larger KBOW · Pittsburgh 25k (BOW)recall@20: 66.4 vs 69.4Mixed
learn w-norm per-location classifiersFV128 · Pittsburgh 25k (FV)recall@1: 33.6 -> 38.3Improved
learn w-norm per-location classifiersFV2048 · Pittsburgh 25k (FV)recall@1: 46.9 -> 50.2Improved
learn w-norm per-location classifiersFV128 · Pittsburgh 55k (FV)recall@1: 10.9 -> 13.5Improved
learn w-norm per-location classifiersFV2048 · 24/7 Tokyo (FV)recall@1: 37.4 -> 42.9Improved
use p-val calibration instead of w-norm (ablation)FV128 · Pittsburgh 25k (FV)recall@1: 33.6 -> 25.3Hurt
use LDA classifiers instead of hinge-loss SVM with hard negatives (ablation)FV128 · Pittsburgh 25k (FV)recall@1: 38.3 -> 31.9Hurt

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