Pith. sign in

REVIEW

Results and findings of the 2021 Image Similarity Challenge

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2202.04007 v1 pith:2YAYASPE submitted 2022-02-08 cs.CV cs.LG

Results and findings of the 2021 Image Similarity Challenge

Zo\"e Papakipos , Giorgos Tolias , Tomas Jenicek , Ed Pizzi , Shuhei Yokoo , Wenhao Wang , Yifan Sun , Weipu Zhang
show 6 more authors
Yi Yang Sanjay Addicam Sergio Manuel Papadakis Cristian Canton Ferrer Ondrej Chum Matthijs Douze
This is my paper
classification cs.CV cs.LG
keywords imagechallengedetectionsimilaritysubmissionsalgorithmicanalysisappears
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

The 2021 Image Similarity Challenge introduced a dataset to serve as a new benchmark to evaluate recent 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 hiding into 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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.