487

participants

Topic provider

ITRI 工業技術研究院成立於1973年,以科技研發,帶動產業發展,創造經濟價值,增進社會福祉為任務;成立四十多年來,累積近3萬件專利,並新創及育成281家公司。

Introduction

With the rapid development of high tech industry, the demand for precision measurement accelerates  especially in quality control techniques. There is a wide variety of applications in using Automated Optical Inspection (AOI) techniques. The outstanding AI performance on image recognition also gives wings to the development of AOI.

 

The goal of this topic is to adopt data science to determine the categories of defects of flexible electronic monitors with a focus to improve AOI techniques.

 

Prize

The following awards will be given to the top three participants whose score on the Private Leaderboard is at least 0.95 higher than the baseline.

 

First place: TWCC services equivalent to a maximum of NT$50,000 based on TWCC pricing

Second place: TWCC services equivalent to a maximum of NT$30,000 based on TWCC pricing

Third place: TWCC services equivalent to a maximum of NT$20,000 based on TWCC pricing

Honorable mention (multiple winners): TWCC services equivalent to a maximum of NT$10,000 based on TWCC pricing

 

* Award eligibility is in accordance with the relevant regulations on the national center for high-performance computing website.

 

Activity time

Time (UTC+8)Event
2020-12-22Registration, and uploading begin
2021-04-23 23:59:59Registration deadline
2021-04-28 23:59:59Upload deadline
2021-05-05Awards announcement

 

Evaluation Criteria

Evaluations are conducted by calculating the Mean Recall, which is the average of all Recalls, and the formula is as follows:

$$mean Recall = {\sum {\text{Number of correct predictions of class} \over \text{Number of total images of class}} \over \text{Number of classes}} $$

 

Rules

  • The evaluation will be based on the final uploaded result. If multiple participants get the same evaluation scores, the time of uploading will determine the ranking.
  • The maximum number of uploading times is 3 times per day.
  • No awards will be given to the participants that are employees (as well as interns and part-time workers) of ITRI or workers from the topic provider. If the award has been given, the prize will be revoked, and the participants will need to return the prize money as well as certificate.
  • This topic does not offer a team-up option, only one account per person is allowed, and each person can only participate once. If any violations are found, people who are involved would be forced to withdraw the activity.
  • All the data, techniques and source codes are original work of participants or are used by permission complying with laws and regulations. If any third-party claims their intellectual property rights or other rights and interests are being violated, the participant will need to handle the disputes personally. If any participants violate intellectual property rights, they will be disqualified, and shall bear legal responsibilities.
  • All the achievements and their IPRs (intellectual property rights) belong to the participants, and the Copyright License Agreements, patent applications, technology transfer and equity distributions of them, should be in accordance with the relevant Laws and Regulations.
  • The organizers reserve the right to enquire the results or take any related actions to examine the submissions.
  • There should be no answer discussions between different accounts, or it will be considered as cheating.
  • If there is cheating or fraud during the activity, the participant that cheats will be disqualified from the activity and the vacancy would be filled up by other participants in the ranking order.
  • After uploading, the answers of test data would be divided into two parts to calculate the score:
    • Before the deadline of the activity: The system will examine and calculate the score refer to the Ground Truth of 40% of the entire test data. The result will be posted on the Public Leaderboard.
    • After the deadline of the activity: The system will examine and calculate the score refer to the Ground Truth of the remaining test data (60%). The result will be posted on the Private Leaderboard as reference for the final score and ranking.
    • Awards will be given to the participants whose score on the Private Leaderboard is higher than the baseline (0.95).
  • Any artificial marking is forbidden.
  • Should there be disputes, the organizer reserves the right to make the final decision.
  • The organizers reserve the right to modify any details regarding the contest when needed.