AI Paper Atlas

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

EDM: Efficient Deep Feature Matching

Xi Li, Tong Rao, Cihui Pan

ICCV 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 7 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 Correlation Injection Module transformer layers (L=2 vs L=0) (ablation)EDM · MegaDepth ablation (1152x1152)AUC@5deg: 51.8 -> 57.5Improved
use L=2 instead of L=4 (ablation)EDM · MegaDepth ablation (1152x1152)AUC@5deg / time: 57.5 -> 57.6; 86.0 ms -> 101.9 msNo clear effect
use deep-narrow feature extractor instead of shallow-wide (ablation)EDM · MegaDepth ablation (1152x1152)AUC@5deg / time: 56.9 -> 57.5; 109.8 ms -> 86.0 msImproved
use QKNA instead of vanilla attention (ablation)EDM · MegaDepth ablation (1152x1152)AUC@5deg: 56.7 -> 57.5Improved
use Injection Layers instead of element-wise sum (ablation)EDM · MegaDepth ablation (1152x1152)AUC@5deg: 55.9 -> 57.5Improved
use top-K coarse selection instead of MNN (ablation)EDM · MegaDepth ablation (1152x1152)AUC@5deg / time: 57.2 -> 57.5; 101.2 ms -> 86.0 msImproved
use focal loss instead of negative log-likelihood for coarse matching (ablation)EDM · MegaDepth ablation (1152x1152)AUC@5deg: 56.3 -> 57.5Improved
add bidirectional refinement (ablation)EDM · MegaDepth ablation (1152x1152)AUC@5deg: 55.7 -> 57.5Improved
add fine selection by sigma (ablation)EDM · MegaDepth ablation (1152x1152)AUC@5deg: 57.0 -> 57.5Improved
use Laplace instead of Gaussian prior distribution (ablation)EDM · MegaDepth ablation (1152x1152)AUC@5deg: 57.1 -> 57.5Improved
add Soft Coordinate Classification (ablation)EDM · MegaDepth ablation (1152x1152)AUC@5deg: 56.5 -> 57.5Improved
use RLE loss instead of L1 loss (ablation)EDM · MegaDepth ablation (1152x1152)AUC@5deg: 53.9 -> 57.5Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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