AI Paper Atlas

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

Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondence

Juhong Min, Seungwook Kim, Minsu Cho

TPAMI 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 22 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 CHM layers (ablation)CHMNet · SPair-71kPCK@0.1: 21.6 -> 46.3Improved
use learnable local CHM instead of global RHM (ablation)CHMNet · SPair-71kPCK@0.1: 38.2 -> 46.3Improved
add last CHM layer (ablation)CHMNet · SPair-71kPCK@0.1: 43.1 -> 46.3Improved
add kernel G (ablation)CHMNet · SPair-71kPCK@0.1: 45.5 -> 46.3Improved
add soft sampler (ablation)CHMNet · SPair-71kPCK@0.1: 43.8 -> 46.3Improved
use semi-isotropic kernel instead of full kernel (4D-4D) (ablation)CHM kernel · SPair-71kPCK@0.1: 43.9 -> 44.5Improved
extend voting space from 4D to 6D (ablation)psi kernel · SPair-71kPCK@0.1: 44.5 -> 46.4Improved
use semi-isotropic kernel instead of full isotropic (4D-4D) (ablation)CHM kernel · SPair-71kPCK@0.1: 39.7 -> 44.5Improved
use full kernel instead of semi-isotropic (6D-4D) (ablation)CHM kernel · SPair-71kPCK@0.1: 46.4 -> 44.8Hurt
use sparse correlation with K=10 nearest neighbors (ablation)CHMNet · SPair-71kPCK@0.1: 46.4 -> 45.2No clear effect
increase scale-space resolution S from 3 to 7 (ablation)CP-CHM CHMNet · SPair-71kPCK@0.1 (F): 51.3 -> 51.6No clear effect
add center-pivot CHM kernelsCHMNet · per-pair inference timetime (ms): 54 -> 32Improved

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