AI Paper Atlas

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

Online Invariance Selection for Local Feature Descriptors

Rémi Pautrat, Viktor Larsson, Martin R. Oswald, Marc Pollefeys

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning

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 soft assignment of meta descriptors instead of hard assignment (ablation)LISRD · HPatchesHEstimation: 0.762 -> 0.784Improved
add meta descriptors instead of greedy selection of local descriptors (ablation)LISRD · HPatchesHEstimation: 0.774 -> 0.784Improved
add online selection over 4 descriptors instead of best single descriptor (ablation)LISRD · HPatchesHEstimation: 0.778 -> 0.784Improved
add 3x3 tiling to meta descriptors (ablation)LISRD · HPatchesHEstimation: 0.752 -> 0.784Improved
use 3x3 tiles instead of 5x5 tiles (ablation)LISRD · HPatchesHEstimation: 0.773 -> 0.784Improved
disentangle four invariance descriptors instead of a single invariant descriptor (ablation)LISRD · HPatchesHEstimation: 0.766 -> 0.784Improved
apply invariance selection to SIFT and Upright SIFTSIFT · HPatches viewpointprecisionImproved
compare LISRD with SuperPoint on illuminationSuperPoint · HPatches illuminationrecall: 0.565 -> 0.655Improved
compare LISRD with SuperPoint on viewpointSuperPoint · HPatches viewpointprecision: 0.595 -> 0.626Improved
LISRD vs SOSNet on homography estimation (coarse meta tiles)SOSNet · HPatches viewpointHEstimation: 0.742 -> 0.688Hurt
LISRD vs SuperPoint on day referenceSuperPoint · DNIM day refrecall: 0.178 -> 0.317Improved
use LISRD descriptors on SIFT keypointsUp-Root SIFT · Aachen Day-Night% localized at 0.5m, 2deg: 54.1 -> 72.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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