AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Enhancing Interpretability in CLIP with Optimal Transport-based Submodular Optimization for Ophthalmic Imaging

Sihong Lu, Jian Yang, Lei Luo

ECCV 2026 · Learning theory and algorithms › Optimal transport · approach: Neural optimal transport · 0 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 visual and text transport costs to the OT stage (ablation)OTSMDL · IDRiDInsertion AUC: 0.406 -> 0.624Improved
add visual and text transport costs to the OT stage (ablation)OTSMDL · OCTDLInsertion AUC: 0.336 -> 0.530Improved
add text transport cost to visual-only cost (ablation)OTSMDL · IDRiDInsertion AUC: 0.487 -> 0.624Improved
add visual transport cost to text-only cost (ablation)OTSMDL · IDRiDInsertion AUC: 0.601 -> 0.624Improved
use unbalanced OT instead of balanced OT (ablation)OTSMDL · IDRiDInsertion AUC: 0.426 -> 0.624Improved
use unbalanced OT instead of balanced OT (ablation)OTSMDL · IDRiDDeletion AUC: 0.313 -> 0.226Improved
use unbalanced OT instead of balanced OT (ablation)OTSMDL · OCTDLInsertion AUC: 0.346 -> 0.530Improved
use score-guided source distribution instead of uniform a (ablation)OTSMDL · IDRiDInsertion AUC: 0.603 -> 0.624Improved
use score-guided source distribution instead of uniform a (ablation)OTSMDL · OCTDLInsertion AUC: 0.529 -> 0.530No clear effect
add importance, contrast and uniqueness scores to submodular initialization (ablation)OTSMDL · IDRiDInsertion AUC: 0.566 -> 0.624Improved
add importance, contrast and uniqueness scores to submodular initialization (ablation)OTSMDL · OCTDLInsertion AUC: 0.506 -> 0.530Improved
use uniqueness score alone instead of importance alone (ablation)OTSMDL · IDRiDInsertion AUC: 0.524 -> 0.612Improved

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