Results and findings of the 2021 Image Similarity Challenge
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F22%3A00361926" target="_blank" >RIV/68407700:21230/22:00361926 - isvavai.cz</a>
Result on the web
<a href="https://proceedings.mlr.press/v176/papakipos22a/papakipos22a.pdf" target="_blank" >https://proceedings.mlr.press/v176/papakipos22a/papakipos22a.pdf</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Results and findings of the 2021 Image Similarity Challenge
Original language description
The 2021 Image Similarity Challenge introduced a dataset to serve as a benchmark to evaluate image copy detection methods. There were 200 participants to the competition. This paper presents a quantitative and qualitative analysis of the top submissions. It appears that the most difficult image transformations involve either severe image crops or overlaying onto unrelated images, combined with local pixel perturbations. The key algorithmic elements in the winning submissions are: training on strong augmentations, self-supervised learning, score normalization, explicit overlay detection, and global descriptor matching followed by pairwise image comparison.
Czech name
—
Czech description
—
Classification
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)
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track
ISBN
—
ISSN
1938-7228
e-ISSN
1938-7228
Number of pages
12
Pages from-to
1-12
Publisher name
Proceedings of Machine Learning Research
Place of publication
—
Event location
Online
Event date
Dec 6, 2021
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—