AI Paper Atlas

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

AFD-Net: Aggregated Feature Difference Learning for Cross-Spectral Image Patch Matching

Dou Quan, Xuefeng Liang, Shuang Wang, Shaowei Wei, Yanfeng Li, Ning Huyan, Licheng Jiao

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 44 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 aggregated multi-level feature differences (AD(5,4), AD(5,4,3), etc.) over a plain Siamese network AD(0) (ablation)AFD-Net · VIS-NIRFPR95 (%): mean improvements 32.20% to 38.98%Improved
aggregate feature differences down to levels 2 and 1 beyond AD(5,4,3) (ablation)AFD-Net · VIS-NIRFPR95 (%)Mixed
add instance normalization on top of batch normalization in shallow layers (IBN vs BN) (ablation)AFD-Net · VIS-NIR (train Country, test 8 categories, mean)FPR95 (%): 1.47 -> 1.08Improved
add batch normalization (BN-LMCL vs no normalization) (ablation)AFD-Net · VIS-NIR (train Country, test 8 categories, mean)FPR95 (%): 2.09 -> 1.47Improved
replace Softmax loss with large margin cosine loss (LMCL) (ablation)AFD-Net · VIS-NIR (train Country, test 8 categories, mean)FPR95 (%): 1.82 -> 1.08Improved
raise LMCL margin m from 0.15 to 0.25 at s=20 (ablation)AFD-Net · VIS-NIR (train Country, test Field)FPR95 (%): 4.12 -> 3.47Improved
raise LMCL margin m from 0.25 to 0.35 at s=20 (ablation)AFD-Net · VIS-NIR (train Country, test Field)FPR95 (%): 3.47 -> 4.86Hurt
use AFD-Net instead of HardNet on cross-spectral matchingAFD-Net DA · VIS-NIR (train Country, test 8 categories, mean)FPR95 (%): 2.80 -> 1.08Improved
use AFD-Net instead of HardNet on single-spectral Brown datasetAFD-Net DA · Multi-view stereo correspondence (Brown, mean of 6 splits)FPR95 (%): 1.51 -> 1.42Improved

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