UG2+ Challenge

Timetable

Challenge Registration and Dry run period**: Janurary 15 ~ May 1, 2021
Final Submissions: April 30 ~ May 1, 2021 (GMT+0 or UTC)
Winner & Runner-ups Docker Image Submission (see guidelines below): May 4, 2021 (GMT+0 or UTC)
Winner Announcement: May 20, 2021

** Dry-run phase: 100 dry-run data for debugging purpose only. This set is provided just to validate your prediction format (so you can work with our final testing in the end). mIoU on this set is not accurate due to small amount of data. Feedback are provided on this dry-run set only.

Prizes

Object detection in poor-visibility environments:
1. (Semi-)supervised object detection in the haze
  - Winner (1st): $1200
  - Runner-up (2nd): $800
  - Runner-up (3rd): $500
2. (Semi-)supervised Face detection in the low light condition
  - Winner (1st): $1200
  - Runner-up (2nd): $800
  - Runner-up (3rd): $500

For a total of about $5K awarded in prizes.

Submission Process

Codalab pages:
1. Track 1.1: https://competitions.codalab.org/competitions/28022
2. Track 1.2: https://competitions.codalab.org/competitions/28029
Dry-run images: downloadable on April 1.
Test images: downloadable April 28 ~ May 1.

Winner/Runner-up Validation Process

Winner and two runner-ups on leaderboard are required to submit their code for the validation. Please follow steps below:

Pull our template docker image: docker pull scaffrey/dsfd_sample:leinao
You may use our default environments in the template docker image, or you may also install specific version of CUDA, Deep Learning Libraries, based on your need.
We will use the two commands below to reproduce your final submission to Codalab:
- docker pull your_dockerhub_id/your_docker_name:tag
- nvidia-docker run -ti -v $host_output_path:/predictions/ -v $host_input_path:/images/ --entrypoint /bin/bash your_dockerhub_id/your_docker_name:tag /run.sh /images /predictions
- run.sh is a bash file where you should put your model inference code inside. A toy example is to put CUDA_VISIBLE_DEVICES=0 python inference.py --input_dir $1 --output_dir $2 inside your run.sh.
- We will then use the same scoring script on Codalab to reproduce your mAP.
As shown in the command above, the input images will be provided to the guest container (/images/) at run time through Docker’s mounting option (-v), as will the output folders (/predictions/) for the model to save their results. Each model must be run on all images contained within the input folder and must save results to output folder location, without any name changes or missing images.
Please validate and pack your running scripts in ONE bash file named run.sh in the docker. We will only run the bash file in each docker. You do not need to include any images or prediction files inside your docker image, as we will use the same testing images for this validation process and we will reproduce the inference.
Commit and push your docker image to Docker Hub and submit your docker link to the corresponding sub challenge by emailing us: cvpr2021.ug2challenge@gmail.com. Note that, the your docker image should inherit from our provided docker template. The organizers will not guarantee to test with the dockers that are built from other templates.
The Docker container must contain all dependencies and code required to perform the model’s inference and will execute the model(s) contained upon run.

Requirements

Software

Docker-CE
NVIDIA Docker

Docker

Our provided Docker will include the following software

Ubuntu 16.04
Pytorch (recommended)
Tensorflow

Hardware

The proposed algorithms should be able to run in systems with:

Up to and including Titan Xp 12 GB
Up to and including 12 cores
Up to and including 32gb memory

If you have any questions about this challenge track please feel free to email cvpr2021.ug2challenge@gmail.com

Rules

Read carefully the following guidelines before submitting. Methods not complying with the guidelines will be disqualified.

We encourage participants to use the provided training and validation data for each task, as well as to make use of their own data or data from other sources for training. However the use any form of annotation or use of any of the provided benchmarks test sets for either supervised or unsupervised training is strictly forbidden.
Team name of submissions on Codalab must match the registration information. Any submission with a team name not registered will not be qualified for prizes. Only a single submission per team can be the winner of a single sub-challenge. Changes in algorithm parameters do not constitute a different method, all parameter tuning must be conducted using the dataset provided and any additional data the participants consider appropriate.

Eligibility

Foreign Nationals and International Developers: All Developers can participate with this exception: residents of, Iran, Cuba, North Korea, Crimea Region of Ukraine, Sudan or Syria or other countries prohibited on the U.S. State Department’s State Sponsors of Terrorism list. In addition, Developers are not eligible to participate if they are on the Specially Designated National list promulgated and amended, from time to time, by the United States Department of the Treasury. It is the responsibility of the Developer to ensure that they are allowed to export their technology solution to the United States for the Live Test. Additionally, it is the responsibility of participants to ensure that no US law export control restrictions would prevent them from participating when foreign nationals are involved. If there are US export control concerns, please contact the organizers and we will attempt to make reasonable accommodations if possible.
If you are entering as a representative of a company, educational institution or other legal entity, or on behalf of your employer, these rules are binding on you, individually, and/or the entity you represent or are an employee. If you are acting within the scope of your employment, as an employee, contractor, or agent of another party, you warrant that such party has full knowledge of your actions and has consented thereto, including your potential receipt of a prize. You further warrant that your actions do not violate your employer’s or entity’s policies and procedures.
The organizers reserve the right to verify eligibility and to adjudicate on any dispute at any time. If you provide any false information relating to the prize challenge concerning your identity, email address, ownership of right, or information required for entering the prize challenge, you may be immediately disqualified from the challenge.
Accounts. For the final testing phase, you may make submissions only under one, unique registration per team. Submission should be made such that the "Team Name" field in Codalab matches your team name in the registration. You will be disqualified if you make submissions for your final testing phase through more than one registration or if your team name cannot be found in the registration. For the final winner validation/confirmation process, eligible teams should submit code containing only ONE algorithms per TEAM. Any submissions that does not adhere to this during the testing or winner validation/confirmation process may be subject to disqualification.

The organizers reserve the right to disqualify any participating team for any of the reasons mentioned above and if deemed necessary.

Warranty, indemnity and release

You warrant that your Submission is your own original work and, as such, you are the sole and exclusive owner and rights holder of the Submission, and you have the right to make the Submission and grant all required licenses. You agree not to make any Submission that: (i) infringes any third party proprietary rights, intellectual property rights, industrial property rights, personal or moral rights or any other rights, including without limitation, copyright, trademark, patent, trade secret, privacy, publicity or confidentiality obligations; or (ii) otherwise violates any applicable state or federal law.

To the maximum extent permitted by law, you indemnify and agree to keep indemnified challenge Entities at all times from and against any liability, claims, demands, losses, damages, costs and expenses resulting from any act, default or omission of the entrant and/or a breach of any warranty set forth herein. To the maximum extent permitted by law, you agree to defend, indemnify and hold harmless the challenge Entities from and against any and all claims, actions, suits or proceedings, as well as any and all losses, liabilities, damages, costs and expenses (including reasonable attorneys fees) arising out of or accruing from: (a) your Submission or other material uploaded or otherwise provided by you that infringes any copyright, trademark, trade secret, trade dress, patent or other intellectual property right of any person or entity, or defames any person or violates their rights of publicity or privacy; (b) any misrepresentation made by you in connection with the challenge; (c) any non-compliance by you with these Rules; (d) claims brought by persons or entities other than the parties to these Rules arising from or related to your involvement with the challenge; and (e) your acceptance, possession, misuse or use of any Prize, or your participation in the challenge and any challenge-related activity.

You hereby release organizers from any liability associated with: (a) any malfunction or other problem with the challenge Website; (b) any error in the collection, processing, or retention of any Submission; or (c) any typographical or other error in the printing, offering or announcement of any Prize or winners.

Competition Framework

The Participant has requested permission to use the dataset as compiled by University of Texas at Austin, Peking University, and University of Chinese Academy of Sciences. In exchange for such permission, Participant hereby agrees to the following terms and conditions:

University of Texas at Austin, Peking University, and University of Chinese Academy of Sciences make no representations or warranties regarding the Dataset, including but not limited to warranties of non-infringement or fitness for a particular purpose.
Pre-trained models are allowed in the competition.
Participants are not restricted to train their algorithms on the provided training set. Collecting and training on additional data is encouraged.

Contact