AI Paper Atlas

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

Cross-Domain Image Matching with Deep Feature Maps

Bailey Kong, James Steven Supančič, Deva Ramanan, Charless C. Fowlkes

IJCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 57 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 per-channel normalization (MCNCC) instead of unnormalized correlation (ablation)NCC on ResNet-50 res2bx · Partial print matchingmAP: 0.15 -> 0.77Improved
use per-channel statistics instead of whole-volume statistics (standardize) (ablation)ResNet-50 res2bx · Partial print matchingmAP: 0.32 -> 0.77Improved
use per-channel MCNCC instead of 3D standardization (ablation)GoogleNet conv2x · Partial print matchingmAP: 0.68 -> 0.81Improved
use per-channel MCNCC instead of 3D standardization (ablation)DeepVGG-16 · Partial print matchingmAP: 0.73 -> 0.76Improved
add per-channel standardization by sigma_c on top of centering (ablation)ResNet-50 res2bx · Partial print matchingmAP: 0.55 -> 0.77Improved
add global PCA decorrelation of channels before MCNCC (ablation)MCNCC on ResNet features · Partial print matchingmAPHurt
add learned per-channel importance weights and CCA projections (ablation)MCNCC · FID-300 whole printstop-1% correct matches: 72.67 -> 79.67Improved
add learned CCA projections and per-channel weights (ablation)MCNCC · FID-300 occlusion study, all printstop-1% correct matches: 72.7 -> 79.0Improved
add joint fine-tuning of projections and weights (ablation)CCA [mu_c,sigma_c.W_c] · Israeli prints (50/50 split)recallNo clear effect
add learned CCA and weights to MCNCC for 1/4 size prints (ablation)MCNCC · FID-300 occlusion study, 1/4 sizetop-10% correct matches: 84.1 -> 79.4Hurt
add learned parameters to MCNCC (ablation)MCNCC · CMP Facade label retrievaltop-1 accuracy: 39.2% -> 96.4%Improved
use MCNCC instead of cosine similarity (ablation)NCC · CMP Facade label retrievaltop-1 accuracy: 18.3% -> 39.2%Improved

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