Image similarity Challenge
CVPR 2021 - NeurIPS 2021
June - December 2021
STATUS: Competition ended -- Site archived
Overview
The goal of this challenge is to determine whether a query image is a modified copy of any image in a reference corpus of size 1 million.
The benchmark features a variety of image transformations such as automated transformations, hand-crafted image edits and machine-learning based manipulations. This mimics real-life cases appearing in social media, for example for integrity-related problems dealing with misinformation and objectionable content.
We expect the DISC21 benchmark to promote image copy detection as an important and challenging computer vision task and refresh the state of the art.
There is a prize pool of $200,000.
The competition ended, but the evaluation dataset and code is available on this website and the competition's github page (see below).
Image similarity
Image similarity (or copy detection) consists of identifying the source of an altered image in a large collection of unrelated images. This technology is applied to a range of content moderation domains, including misinformation, copyright infringement, scams and others.
Image similarity detection, a method of content tracing for visual data, has not received enough attention within the computer vision community despite its growing importance for detecting manipulation and improving the detection of data provenance.
Links
Submission site (with data, detailed description, leaderboard):
Matching Track: https://www.drivendata.org/competitions/79/
descriptor track: https://www.drivendata.org/competitions/80/
Paper about the challenge and DISC21 dataset: https://arxiv.org/abs/2106.09672
Baseline code to get started with the task and submissions: https://github.com/facebookresearch/isc2021
Sponsors
Sponsor: Meta
Co-supporters: Pinterest, BBC, Getty Images, iStock and Shutterstock