Dark Side Augmentation: Generating Diverse Night Examples for Metric Learning

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F23%3A00370501" target="_blank" >RIV/68407700:21230/23:00370501 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.1109/ICCV51070.2023.01024" target="_blank" >https://doi.org/10.1109/ICCV51070.2023.01024</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICCV51070.2023.01024" target="_blank" >10.1109/ICCV51070.2023.01024</a>

Result language

angličtina

Original language name

Dark Side Augmentation: Generating Diverse Night Examples for Metric Learning

Original language description

Image retrieval methods based on CNN descriptors rely on metric learning from a large number of diverse examples of positive and negative image pairs. Domains, such as night-time images, with limited availability and variability of training data suffer from poor retrieval performance even with methods performing well on standard benchmarks. We propose to train a GAN-based synthetic-image generator, translating available day-time image examples into night images. Such a generator is used in metric learning as a form of augmentation, supplying training data to the scarce domain. Various types of generators are evaluated and analyzed. We contribute with a novel light-weight GAN architecture that enforces the consistency between the original and translated image through edge consistency. The proposed architecture also allows a simultaneous training of an edge detector that operates on both night and day images. To further increase the variability in the training examples and to maximize the generalization of the trained model, we propose a novel method of diverse anchor mining. The proposed method improves over the state-of-the-art results on a standard Tokyo 24/7 day-night retrieval benchmark while preserving the performance on Oxford and Paris datasets. This is achieved without the need of training image pairs of matching day and night images. The source code is available at https://github.com/mohwald/gandtr.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

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

Project

<a href="/en/project/EF16_019%2F0000765" target="_blank" >EF16_019/0000765: Research Center for Informatics</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Publication year

2023

Confidentiality

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

Article name in the collection

ICCV2023: Proceedings of the International Conference on Computer Vision

ISBN

979-8-3503-0719-1

ISSN

1550-5499

e-ISSN

2380-7504

Number of pages

11

Pages from-to

11119-11129

Publisher name

IEEE

Place of publication

Piscataway

Event location

Paris

Event date

Oct 2, 2023

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

001169499003054