AI Paper Atlas

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

Manifold Embedding of Deep Image Features for Image Matching via Neural Adjoint Maps

Nafie El Amrani, Moritz Heep, Florian Bernard

NeurIPS 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a manifold-based embedding of deep image features, using neural adjoint maps, to regularise semantic image correspondence beyond plain nearest-neighbour matching on foundation model features.

Problem

Semantic correspondence between different object instances of similar categories in real-world images is hard, and nearest-neighbour matching on foundation model features is insufficiently regularised.

Approach

Embeds deep image features on a manifold and uses neural adjoint maps to regularise matching, rather than relying on raw nearest-neighbour matching in feature space. Only the abstract is available, so details are limited.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use proposed manifold-embedding LBO instead of the image graph Laplacian (ablation)NAMI with NAM · SPair-71kPCK@0.1 (%): 38.96 -> 56.50Improved
use neural adjoint map instead of linear SmoothFM (ablation)NAMI with proposed LBO · SPair-71kPCK@0.1 (%): 50.13 -> 56.50Improved
use NAMI instead of Cheng et al.Cheng et al. functional maps for images · TSSruntime (s): 95.6 -> 0.76Improved
use NAMI instead of Cheng et al. at 50 eigenfunctionsCheng et al. · TSSPCK@0.05 (%): 60.3 -> 84.3Improved
increase eigenfunctions beyond 50 (ablation)NAMI · TSSPCK@0.05 (%): 84.3 (k=50) -> 80.0 (k=200)Hurt
add Neural ZoomOut refinement (ablation)NAMI · TSSPCK@0.05 (%): 84.3 -> 86.3 at roughly 10x runtimeImproved
add feature refinement network from Cheng et al. (ablation)NAMI · TSSPCK@0.05 (%): 86.72 -> 81.84Hurt
use NAMI versus best baseline on large rotationsNAMI · Faust-2D hard splitPCKNo clear effect
use NAMI instead of Fuse2MatchFuse2Match · SPair-71kPCK@0.1 (%): 61.0 -> 56.5Hurt

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