AI Paper Atlas

Research map / Detection and segmentation / CNN features

Joint Detection and Matching of Feature Points in Multimodal Images

Elad Ben Baruch, Yosi Keller

TPAMI 2021 · Detection and segmentation › CNN features · approach: Context for hard detection conditions · 40 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 hard negative mining (ablation)Hybrid CNN (CL) · UVIS-NIR ablation (En et al. setup)FPR95 (%): 9.90 -> 3.41Improved
add hard negative mining (ablation)Hybrid CNN (CE) · UVIS-NIR ablation (En et al. setup)FPR95 (%): 5.78 -> 3.66Improved
add auxiliary losses L_S and L_A (3 losses vs 1) (ablation)Hybrid CNN (CL) · UVIS-NIR ablation (En et al. setup)FPR95 (%): 4.52 -> 3.41Improved
add auxiliary losses L_S and L_A (3 losses vs 1) (ablation)Hybrid CNN (CE) · UVIS-NIR ablation (En et al. setup)FPR95 (%): 4.72 -> 3.66Improved
use Hybrid instead of symmetric-only network (ablation)CL, single loss · UVIS-NIR ablation (En et al. setup)FPR95 (%): 9.56 -> 4.52Improved
use Hybrid instead of symmetric-only network (ablation)CE, single loss · UVIS-NIR ablation (En et al. setup)FPR95 (%): 4.2 -> 4.72Hurt
use Hybrid instead of asymmetric-only network (ablation)CE, single loss · UVIS-NIR ablation (En et al. setup)FPR95 (%): 5.8 -> 4.72Improved
use Hybrid instead of asymmetric-only network (ablation)CL, single loss · UVIS-NIR ablation (En et al. setup)FPR95 (%): 4.32 -> 4.52No clear effect
use deeper CNN backbone (D-Hybrid-CL) instead of base CNN (ablation)Hybrid-CL · VIS-NIR (Aguilera split, Mean over 9 categories)FPR95 (%): 1.93 -> 1.7Improved
replace Contrastive loss with Cross-Entropy (ablation)Hybrid CNN · UVIS-NIR (En et al. split)FPR95 (%): 3.41 -> 3.66No clear effect
Hybrid CNN versus TS-NetHybrid-CL · CUHK (En et al. split)FPR95 (%): 2.77 -> 0.1Improved
Hybrid CNN versus HardNetHybrid-CL · VIS-NIR (Aguilera split, Mean over 9 categories)FPR95 (%): 2.80 -> 1.93Improved

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