AI Paper Atlas

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

Deep Graphical Feature Learning for the Feature Matching Problem

Zhen Zhang, Wee Sun Lee

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 74 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 global pooling layer (ablation)CMPNN geometric feature net · Synthetic, with outliersaccuracyImproved
add global pooling layer (ablation)CMPNN geometric feature net · Synthetic, no outliersaccuracyNo clear effect
use a deeper network (repeat second CMPNN layer three times) instead of normal (ablation)CMPNN geometric feature net · Synthetic (noise 0.05)accuracyNo clear effect
use a deeper/wider network instead of normal (ablation)CMPNN geometric feature net · Synthetic (noise 0.05)GPU memory: 76 -> 103 MB deeper; 76 -> 297 MB widerHurt
use normal depth/width instead of shallower or narrower (ablation)CMPNN geometric feature net · Synthetic (noise 0.05)accuracyImproved
use output dim 64 instead of 8 (ablation)CMPNN geometric feature net · Synthetic (outliers + rotation)accuracyImproved
use output dim 512 instead of 4096 (ablation)CMPNN geometric feature net · Synthetic (outliers + rotation)accuracyImproved
use output dim 512 instead of 64 (ablation)CMPNN geometric feature net · Synthetic (outliers + rotation)accuracyNo clear effect
learn local features with CMPNN instead of PointNetPointNet baseline · Pascal-PF (original points)matching accuracy: 69.7 -> 88.5Improved
learn local features with CMPNN instead of PointNetPointNet baseline · Pascal-PF (random rotation)matching accuracy: 41.5 -> 69.9Improved
apply random rotation to input pointsOurs · Pascal-PFmatching accuracy: 88.5 -> 69.9Hurt
apply random rotation to input pointsPointNet · Pascal-PFmatching accuracy: 69.7 -> 41.5Hurt

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