Topic provider

Pervasive Artificial Intelligence Research (PAIR) Labs, Ministry of Science and Technology (MOST), Taiwan

The Pervasive AI Research (PAIR) Labs, a group of national research labs funded by the Ministry of Science and Technology (MOST), Taiwan, is commissioned to achieve academic excellence, nurture local AI talents, build international linkage, and develop pragmatic approaches in the areas of applied AI technologies toward services, products, workflows, and supply chains innovation and optimization. PAIR is constituted of 13 distinguished research institutes in Taiwan to investigate various of applied AI topics.
Website: https://pairlabs.ai/

Intelligent Vision System (IVS) Lab, National Chiao Tung University (NCTU), Taiwan

The Intelligent Vision System (IVS) Lab at the National Chiao Tung University is directed by Professor Jiun-In Guo to tackle practical open problems in autonomous driving research, esp. on intelligent vision processing systems, applications, and SoC exploiting deep learning technology.
Website: http://ivs.ee.nctu.edu.tw/ivs/


Object detection in the computer vision area has been extensively studied and making tremendous progress in recent years using deep learning methods. However, due to the heavy computation required in most deep learning-based algorithms, it is hard to run these models on embedded systems, which have limited computing capabilities. In addition, the existing open datasets for object detection applied in ADAS applications usually include pedestrian, vehicles, cyclists, and motorcycle riders in western countries, which is not quite similar to the crowded Asian countries with lots of motorcycle riders speeding on city roads, such that the object detection models trained by using the existing open datasets cannot be directly applied in detecting moving objects in Asian countries.

In this competition, we encourage the participants to design object detection models that can be applied in the competition’s traffic with lots of fast speeding motorcycles running on city roads along with vehicles and pedestrians. The developed models not only can fit for embedded systems but also can achieve high accuracy at the same time.

This competition is divided into two stages: qualification and final competition.

  • Qualification competition: all participants submit their answers online. A score is calculated. The top 15 teams would be qualified to enter the final round of the competition.

  • Final competition: the final score will be validated and evaluated over NVIDIA Jetson TX2 by the organizing team for the final score.

The goal is to design a lightweight deep learning model suitable for constrained embedded system design to deal with traffic in Asian countries. We focus on detection accuracy, model size, computational complexity, and performance optimization on NVIDIA Jetson TX2 based on a predefined metric.

Given the test image dataset, participants are asked to detect objects belonging to the following four classes {pedestrian, vehicle, scooter, bicycle} in each image, including class and bounding box.

Prize Information

According to the points of each team in the final evaluation, we select the highest three teams for cash awards.

  1. Champion: $USD 1,500

  2. 1st Runner-up: $USD 1,000

  3. 2nd Runner-up: $USD 750

Special Awards

  1. Best accuracy award – award for the highest mAP in the final competition: $USD 200;

  2. Best bicycle detection award – award for the highest AP of bicycle recognition in the final competition: $USD 200;

  3. Best scooter detection award – award for the highest AP of scooter recognition in the final competition: $USD 200;

All the award winners must agree to submit contest paper, allow to open source the final codes, and attend the ICME2020 Grand Challenge PAIR Competition Special Session to present their work.

Activity time

12/1/2019Qualification Competition Start Date
12/1/2019Date to Release Public Testing Data
1/24/2020Date to Release Private Testing Data for Qualification
1/30/2020 12:00 PM UTCQualification Competition End Date
2/1/2020 12:00 AM UTCFinalist Announcement
2/1/2020Final Competition Start Date
2/7/2020Date to Release Private Testing Data for Final
2/14/2020 12:00 PM UTCFinal Competition End Date
3/1/2020 12:00 PM UTCAward Announcement
3/13/2020Paper Submission Date
4/15/2020Author notification
4/29/2020Camera-ready submission

Evaluation Criteria

  • Qualification Competition

    The grading rule is based on MSCOCO object detection rule.

    • The mean Average Precision (mAP) is used to evaluate the results.

    • Intersection over union (IoU) threshold is set at 0.5.

    The resulting average precision (AP) of each class should be calculated and the mAP over all classes is evaluated as the key metric.

    Besides, during the qualification competition period, each team has to submit a team composition document, including team name, leader, team members, affiliation, and contact information, etc.

  • Final Competition

    • Accuracy(mAP)–25 %

      The team with the highest accuracy will get the full score (25%) and the team with the lowest one will get zero. The rest teams will get scores directly proportional to the mAP difference.

    • Model size (number of parameters * bit width used in storing the parameters)–25 %

      The team with the smallest model will get the full score (25%) and the team with the largest one will get zero. The rest teams will get scores directly proportional to the model size difference.

    • Computational Complexity(GOPs/frame)–25 %

      The team with the smallest GOP number per frame will get the full score (25%) and the team with the largest one will get zero. The rest teams will get scores directly proportional to the GOP value difference.

    • Speed on NVIDIA Jetson TX2–25 %

      The team with a model to complete the detection task in the shortest time will get the full score (25%) and the team that takes the longest time will get zero score. The rest teams will get scores directly proportional to the execution time difference.

    • The speed evaluation procedure will measure the time of the overall process from reading the private testing dataset in final to completing submission.csv file, including parsing image list, loading images, and any other overhead to conduct the detection through the testing dataset.

[1] Average Precision (AP):

[2] intersection over union (IoU):


Coordinator Contacts

Prof. Ted Kuo, tkuo@nctu.edu.tw

Prof. Jenq-Neng Hwang, hwang@uw.edu

Prof. Jiun-In Guo, jiguo@nctu.edu.tw

Chia-Chi Tsai, apple.35932003@gmail.com


  • Team mergers are not allowed in this competition.
  • Each team can consist of a maximum of 6 team members.
  • The task is open to the public. Individuals, institutions of higher education, research institutes, enterprises, or other organizations can all sign up for the task.
  • A leaderboard will be set up and make available publicly.
  • Multiple submissions are allowed before the deadline and the last one will be used to enter the final qualification consideration.
  • Privately sharing code or data outside of teams is not permitted. It's okay to share code if made available to all participants on the forums.
  • Personnel of IVSLAB team are not allowed to participate in the task.
  • A common honor code should be observed. Any violation will be disqualified.