AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-Level Retrieval

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F25%3A00378907" target="_blank" >RIV/68407700:21230/25:00378907 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/978-3-031-73202-7_18" target="_blank" >https://doi.org/10.1007/978-3-031-73202-7_18</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-73202-7_18" target="_blank" >10.1007/978-3-031-73202-7_18</a>

Jazyk výsledku

angličtina

Název v původním jazyce

AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-Level Retrieval

Popis výsledku v původním jazyce

This work investigates the problem of instance-level image retrieval re-ranking with the constraint of memory efficiency, ultimately aiming to limit memory usage to 1KB per image. Departing from the prevalent focus on performance enhancements, this work prioritizes the crucial trade-off between performance and memory requirements. The proposed model uses a transformer-based architecture designed to estimate image-to-image similarity by capturing interactions within and across images based on their local descriptors. A distinctive property of the model is the capability for asymmetric similarity estimation. Database images are represented with a smaller number of descriptors compared to query images, enabling performance improvements without increasing memory consumption. To ensure adaptability across different applications, a universal model is introduced that adjusts to a varying number of local descriptors during the testing phase. Results on standard benchmarks demonstrate the superiority of our approach over both hand-crafted and learned models. In particular, compared with current state-of-the-art methods that overlook their memory footprint, our approach not only attains superior performance but does so with a significantly reduced memory footprint. The code and pretrained models are publicly available at: https://github.com/pavelsuma/ames

Název v anglickém jazyce

AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-Level Retrieval

Popis výsledku anglicky

This work investigates the problem of instance-level image retrieval re-ranking with the constraint of memory efficiency, ultimately aiming to limit memory usage to 1KB per image. Departing from the prevalent focus on performance enhancements, this work prioritizes the crucial trade-off between performance and memory requirements. The proposed model uses a transformer-based architecture designed to estimate image-to-image similarity by capturing interactions within and across images based on their local descriptors. A distinctive property of the model is the capability for asymmetric similarity estimation. Database images are represented with a smaller number of descriptors compared to query images, enabling performance improvements without increasing memory consumption. To ensure adaptability across different applications, a universal model is introduced that adjusts to a varying number of local descriptors during the testing phase. Results on standard benchmarks demonstrate the superiority of our approach over both hand-crafted and learned models. In particular, compared with current state-of-the-art methods that overlook their memory footprint, our approach not only attains superior performance but does so with a significantly reduced memory footprint. The code and pretrained models are publicly available at: https://github.com/pavelsuma/ames

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GM21-28830M" target="_blank" >GM21-28830M: Učení Univerzální Vizuální Reprezentace s Omezenou Supervizí</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Computer Vision – ECCV 2024, Part LIX

ISBN

978-3-031-73201-0

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

19

Strana od-do

307-325

Název nakladatele

Springer, Cham

Místo vydání

—

Místo konání akce

Milano

Datum konání akce

29. 9. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001401048900018