Cui Qinghua's team won the first prize in the Google Universal Image Embedding Research Competition

Recently, Professor Cui Qinghua and doctoral student Shao Shihao of the Department of Medical Bioinformatics of Peking University School of Basic Medicine held the just-concluded Google Universal Image Embedding Competition won the championship
.
This competition is the designated competition of the European Conference on Computer Vision (ECCV), one of the top conferences in the field of computer vision, attracting 1022 teams from the United States, Germany, France, Japan, Australia and other countries to participate.
The participants are mainly
related to computer and artificial intelligence professional institutions.
The competition is an annual Instance-Level Recognition (ILR) series of competitions, called instance-level recognition It is a computer vision task that recognizes a specific instance of an object rather than simply identifying the category, which has great application prospects in the field of extensive image search and matching (such as Baidu image recognition, Google image recognition), and this kind of computer vision algorithm also has potential application value
in the field of medical image intelligent analysis.

The main page of this contest

In this competition, Professor Cui Qinghua and Shao Shihao proposed a scheme for pre-training VIT-H based on CLIP under Laion-2B, established a new training and fine-tuning method, analyzed the model fusion scheme and feasibility under the situation of feature vector space inconsistency, and finally began with The scores of 0.
732 and 0.
728 ranked first in both the open data and blind test data rankings, and the details of the method are published here style="font-family:" _istranslated="1">
。 In view of these excellent results, the duo was also invited to attend the European Computer Vision Conference to be held in Tel Aviv, Israel, and gave a live oral presentation
.
The proposed algorithm has significantly improved the task of instance-level image target recognition and is expected to be applied to the intelligent analysis
of medical images.

Shao Shihao, an eight-year doctoral student in basic medicine in 2017, is committed to proposing new artificial intelligence algorithms to solve problems in the field of computer vision and applying them to medical image intelligent analysis and processing under the guidance of Professor Cui Qinghua Challenge winner) and gastrointestinal tumor image segmentation (University of Wisconsin UW-Madison GI Tract Image Segmentation Competition Gold Medal) have been successfully applied
.
This work has been supported
by the National Science Foundation for Outstanding Young Scholars, the Innovation Group of the National Natural Science Foundation of China and other funds.

Screenshot of the ranking page of this competition

(School of Basic Medicine, Peking University)