AI Paper Atlas

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

Beyond Cartesian Representations for Local Descriptors

Patrick Ebel, Anastasiia Mishchuk, Kwang Moo Yi, Pascal Fua, Eduard Trulls

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 84 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 log-polar instead of cartesian patches at lambda=12 (ablation)descriptor network · New datasetFPR95: 0.72 -> 0.67Improved
enlarge support region to lambda=96 with log-polar patches (ablation)log-polar descriptor · New datasetFPR95: 0.67 -> 0.36Improved
enlarge support region from lambda=12 to 96 with cartesian patches (ablation)cartesian descriptor · New datasetFPR95: 0.72 -> 7.03Hurt
increase lambda beyond 96 for log-polar patches (ablation)log-polar descriptor · New datasetFPR95: 0.36 -> 0.36No clear effect
use log-polar instead of cartesian at lambda=96 on AMOS (ablation)descriptor network · AMOS patchesrank-1: 0.481 -> 0.651Improved
enlarge lambda from 12 to 96 with log-polar patches (ablation)log-polar descriptor · HPatches illumination splitrank-1: 0.729 -> 0.774Improved
enlarge lambda from 12 to 96 with cartesian patches (ablation)cartesian descriptor · HPatches viewpoint splitrank-1: 0.828 -> 0.681Hurt
enlarge lambda from 12 to 96 with log-polar patches (ablation)log-polar descriptor · HPatches viewpoint splitrank-1: 0.833 -> 0.847Mixed
enlarge lambda from 16 to 96 with log-polar patches (ablation)log-polar descriptor · PhotoTourism stereo taskmAP at 15 deg: 0.0420 -> 0.0448Improved
use log-polar lambda=96 instead of cartesian lambda=16 (ablation)descriptor network · PhotoTourism multi-view taskmAP at 15 deg: 0.5208 -> 0.5427Improved
use log-polar descriptor instead of HardNetdescriptor network · New datasetFPR95: 0.98 -> 0.36Improved

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