AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

ELViS: Efficient Visual Similarity from Local Descriptors that Generalizes Across Domains

Pavel Suma, Giorgos Kordopatis-Zilos, Yannis Kalantidis, Giorgos Tolias

ICLR 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Augmentation and mixture-of-experts generalization · 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
remove dustbins from optimal transport (ablation)ELViS · 8 datasets (GLDv2-trained)mAP avg: 53.9 -> 30.4Improved
use descriptor-dependent dustbin gains instead of a scalar gain (ablation)ELViS · 8 datasets (GLDv2-trained)mAP avg: 51.5 -> 53.9Improved
add learnable vote function f (ablation)ELViS · 8 datasets (GLDv2-trained)mAP OOD: 53.8 -> 55.0Improved
add learnable vote function f (ablation)ELViS · 8 datasets (GLDv2-trained)mAP ID: 50.5 -> 50.8Hurt
add learnable loss function g during training (ablation)ELViS · 8 datasets (GLDv2-trained)mAP avg: 48.5 -> 53.9Improved
add f and g together (ablation)ELViS · 8 datasets (GLDv2-trained)mAP avg: 48.2 -> 53.9Improved
add learnable descriptor projection (ablation)ELViS · 8 datasets (GLDv2-trained)mAP avg: 50.8 -> 53.9Improved
use lambda 0.01 instead of 0.1 for OT entropy regularization (ablation)ELViS · 8 datasets (GLDv2-trained)mAP avg: 53.9 -> 47.4Hurt
use lambda 1.0 instead of 0.1 for OT entropy regularization (ablation)ELViS · 8 datasets (GLDv2-trained)mAP avg: 53.9 -> 48.4Hurt
make lambda learnable (ablation)ELViS · 8 datasets (GLDv2-trained)mAP avg: 53.9 -> 54.0No clear effect
increase Sinkhorn iterations from 1 to 20 (ablation)ELViS · 8 datasets (GLDv2-trained)mAP avg: 52.7 -> 54.1Improved
replace AMES with ELViS (similarity-space model) for re-ranking, trained on SOPAMES · out-of-domain datasets (SOP-trained)mAP OOD: 41.4 -> 51.0Improved

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