• January 31, 2019: Development kit and registration made available
  • April 5 - April 20, 2019: Dry run period**
  • April 1, 2019: Registration deadline
  • May 1, 2019: Submissions deadline
  • May 20, 2019: Challenge results will be released
  • June 16, 2019: Most successful and innovative teams present at CVPR 2019 workshop
** Every contestant will have the opportunity to verify before the submission window closes that their Singularity container submission works. This dry run is completely optional but is highly recommended.


UG2+ evaluates algorithms for enhancement of images/videos at scale. The most successful and innovative teams will be invited to present at the CVPR 2019 workshop. We provide two sub-challenge categories:

  1. Video object classification and detection from unconstrained mobility platforms:
    1. Object Detection Improvement on Video
      • 1st Place: $15K
      • 2nd Place: $10K
    2. Object Classification Improvement on Video
      • 1st Place: $15K
      • 2nd Place: $10K
For a total of $50K awarded in prizes.


For your submission, follow these steps:

  1. Download the training datasets and the Development Kit.
  2. Develop your solution and evaluate it on the validation sets (the evaluation code will be provided in the Development Kit).
  3. Please make sure that:
    • Your algorithms can take all images from the "home/input/" directory as input
    • You output the results into "home/output/alg#/" (# refers to the number of the algorithm submission[0-2]). Make sure that the input file names are preserved (that is, img0.png should be processed by your algorithm and saved as img0.png in the output folder for your algorithm).
  4. Pack all your code into the singularity container (see the Devkit README for more information on this), and make sure the organizers can run it and can generate the output files with the provided algorithm based on the given input files. Also, a README file explaining how your algorithms work and how to change the running behavior of the algorithms are welcomed.
  5. Upload your compiled Singularity image to Google Drive (or any cloud service) and submit your link to the corresponding sub-challenge. Note that, your Singularity container should inherit from our provided Singularity recipe template. The organizers will not guarantee to test with the dockers that are built from other recipe files.
  6. Each team may submit up to 3 algorithms per sub challenge. All submissions (per sub challenge) will be held within one single Singularity image. The Singularity image will contain all dependencies and code required to perform the model’s operation and will execute the model(s) contained upon run.

Development Kit

The Development Kit consists of a Singularity recipe file containing the basic structure for the algorithm submission, as well as instructions on how to use, and compile into an executable image. The images, annotation, and lists specifying the training/validation sets for the challenge are provided separately, and can be obtained on our Dataset page.

Additional files to process the dataset as well as to evaluate their algorithm's performance for each track is also provided.


  • Singularity
  • CUDA 8.0
  • cuDNN v5.0

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


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

  • Participants are expected to develop robust solutions to improve the visual task of a given sub-challenge, thus it is not allowed to tailor different methods or to alter the parameters of a method for any individual benchmark dataset (or subset of any of the datasets). A submission whose method is trained separately on a subset of a benchmark, resulting in different parameters/weights for any other subset or dataset of a given sub-challenge, or that employs a classifier to identify a given input benchmark or subset will be considered invalid. Moreover, a method who makes use of the knowledge of some labels corresponding to any specific benchmark, or that executes separate program paths designed specifically for individual datasets will also be considered in violation of these guidelines.
  • 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.
  • Participants who have investigated several algorithms may submit up to 3 algorithms per challenge. Only a single submission per participant 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.
  • The algorithms designed must process each image or sequence of images (for sub-challenges centered in video enhancement) provided in a designated input folder, and save the enhanced versions under the same image name at a designated output folder. That is, an image input/0.jpg would be saved by the first algorithm proposed by the participants in output1/0.png.
  • If an algorithm is submitted that makes inefficient use of deep learning, we may not be able to process the entire test set due to time constraints. To avoid this possibility, we will place limits on per-image runtime.
  • Results can vary based on the GPU used. We noticed that results varied slightly across GPU models. We are restricting our evaluation to one model (TitanXP) and will encourage participants to use this model in their development.


  • 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.

  • Individual Account. You may make submissions only under one, unique registration. You will be disqualified if you make submissions through more than one registration. You may submit up to 2 submissions (one per challenge), containing at most 3 algorithms per submission. Any submissions that does not adhere to this will be disqualified.

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

Note that challenge deadlines are subject to change and additional hurdle deadlines may be introduced during the challenge. Any additional or altered deadlines not already described in these challenge rules will be publicized to the participants via the challenge website. It is the Participant's responsibility to check the website regularly throughout the challenge to stay informed of any new or updated deadlines. The organizers are not responsible for any Participant's failure to do so. You may only participate using a single, unique registration. The Participant has requested permission to use the UG2 datasets. In exchange for such permission, the Participant hereby agrees to the following terms and conditions

  • The organizers make no representations or warranties regarding the datasets, 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 UG2 datasets. Collecting and training on additional data is encouraged.