DogAge Challenge

Welcome to the page for the ML challenge “Automatic Estimation of Dog Age”




Challenge participants are kindly required to register for challenge participation by August 20th using this form. Only registered participants will be eligible for the prize. 

Submissions are received (via email to with subject DogAge Challenge Submission) until September 10, 2019. Multiple resubmissions are allowed until this deadline (up to 5 resubmissions by each participant) to improve the solutions.

The winners will be announced at the ICANN’19 conference. To receive the prize, the winners must attend the conference.



Automatic age estimation is a challenging problem attracting attention of the computer vision and pattern recognition communities due to its many practical applications. Arti cial neural networks, such as CNNs are a popular tool for tackling thiד problem, and several datasets which can be used for training models are available.

Despite the fact that dogs are the most well studied species in animal science, and that ageing processes in dogs are in many aspects similar to those of humans, the problem of age estimation for dogs has so far been overlooked.


The goal of this challenge is developing models that will accurately predict apparent dog age. 


Read more about the challenge here.


This challenge is based on the DogAge dataset that has been carefully collected in a collaboration between animal and computer
scientists. It contains images of dogs, mapping them to one of the three classes young (0 -2 years), adult (2 – 5 years) or senior (> 6 years).

The dataset currently consists of two parts:
1. Expert data: contains 1373 images collected by animal scientists, sampling pet dogs, shelter dogs, laboratory dogs, working dogs and commercial kennel dogs. Their age and division into the three groups was carefully veri fied. The images are mostly high-quality portraits with the dog facing upwards forward.
2. Pet finder data: contains 26190 images collected using the APIs of Petfi nder, a portal for pet adoption. The division of dogs into groups is not verfi ed, and there is a diversity of angles and distances of the photos. The raw data has been cleaned, removing photos with more than one dog, containing pets or large parts of humans, and low quality images.


The two parts of the dataset together with the testing set can be found here.




This challenge is organized by:

ICANN’19: International Conference on Artificial Neural Networks

Tech4Animals Lab, University of Haifa

ETU “LETI” St. Petersburg

School of Biology and Environmental Sciences, University of Salford


Important Dates:

Solution Submission opens: May 1, 2019

Solution Submission closes: September 10, 2019

Winner Announcement: September 14-17, at the ICANN’19



Dear DogAge Challenge Participants,


We are very happy to see a lot of interest generated by our challenge, and hope that this will provide a boost to the area of ML for animal science&welfare!

The proposers of the best and most interesting solutions will be invited to participate in a collaborative journal paper summarizing the challenge and its results, which we plan to submit to a high quality journal on AI & ML (e.g., “Engineering Applications of Artificial Intelligence” or other – to be decided by the collaborators) by the end of 2019.

The winners of the challenge will be announced at the ICANN 2019 conference in Munich in September, and the first three places will receive a prize (the exact sum will depend on the number of winners among whom the prize will be distributed).


We have set up a submission website here:

The deadline for solution submission is 10 September.

The submitted solution should be a pdf file of up to 5 pages, which contains the following information:

  1. Author name and affiliation
  2. A high-level description of the model
  3. Implementation details needed to run the model (environment, packages used, etc.)
  4. A (working!) link to the csv file containing the solution to the DogAge19 testing set. The csv file should contain two comma separated columns: image file name (dog1.jpg) and the predicted class: 0 – adult, 1 – senior, 2 – young.


The submitted solutions will be compared using the three metrics AR, MAE and CE as explained in



For any questions, we are here for you – please email Anna Zamansky at

Best wishes and looking forward to your solutions!

The DogAge Challenge Team