1st SSLAD Challenge

The challenge website has been released at CodaLab.

This challenge is a part of ICCV2021 workshop "Self-supervised Learning for Next-Generation Industry-level Autonomous Driving". The aim of this track is to utilize both labeled data and unlabled data to achieve industry-level autonomous driving solutions

For 2D object detection track(Track1), we provide a real-word training dataset with 10 million images of which 5K are labeled and 5K/10K validation/testing labeled images for evaluation. This dataset has been collected throughout diverse scenarios in cities in China and contains scenes in a wide variety of places, objects and weather conditions such as highways, city streets, country roads, raining weather, etc.

For continue learning track(Track3A/3B), Track 3A focuses on continual classification, providing a natural stream of data from cars driving in China, collected over three days. This challenging track has highly class-imbalanced data (e.g. seeing significantly more cars than pedestrians), and includes domain shifts from day to night in different cities and weather conditions. Track 3B focuses on continual 2D Object Detection in a domain-incremental fashion, using the domain shifts in the classification track to group the data into tasks.

This challenge has been released before August 1st, 2021 to enable participants to evaluate their techniques. Challenge participants with the most successful and innovative entries will be invited to present at this workshop and will receive awards. A 10,000 USD cash prize will be awarded to the top performers in each task and 2nd and 3rd places will be awarded with 5,000 USD.

Winners of Each Track

Track Prize Team Member Affiliation
Track1 First Prize Yingjia Bu, Chengfeng Xu, Shida Zheng,Mengyue Zhang,Jiexiang Wang,Chenhao Li,Tao Hu,Chenshu Chen, Jin Wang,Dahu Shi,Wenming Tan Hikvision Research Institute
Second Prize Beitong Zhou, Donghao Gu, Binbin Zhang, Sanli Tang, Yunlu Xu, Zhanzhan Cheng, Yi Niu GOLDWAY ITS CO. LTD
Third Prize Xiaoqiang Lu, Guojin Cao, Zixiao Zhang, Mengjiao Wang, Yuting Yang, Licheng Jiao Xidian University
Track3A First Prize Gabriele Graffieti, Guido Borghi, Matteo Ferrara, Davide Maltoni University of Bologna
Second Prize Azamat Sabyrbayev BTS Digital
Third Prize Muhammad Rifki Kurniawan Xi’an Jiaotong University
Track3B First Prize Duo Li, Guimei Cao, Xunlu Xu, Zhanzhan Cheng, Yi Niu Hikvision Research Institute
Second Prize Manoj Acharya, Chris Kanan Rochester Institute of Technology
Third Prize Xialei Liu, Jiangtian Zhai Nankai University

Technical Reports

The technical reports of winner of Track1 can be found in: [First Prize] [Second Prize] [Third Prize]
The technical reports of winner of Track3A can be found in: [First Prize] [Second Prize] [Third Prize]
The technical reports of winner of Track3B can be found in: [First Prize] [Second Prize] [Third Prize]