Can you make Machine Learning models to Recognize Landmarks?

Google is organizing the 4th iteration of its Landmark Recognition Challenge on Kaggle- The Google Landmark Recognition 2021 Challenge. With the help of this completion, Google aims to leverage the Machine Learning practitioners community on Kaggle to help recognize landmarks in images. Recognizing landmarks in images can have tremendous uses cases in helping people to organize and filter images in their galleries. This competition is very much similar to the previous iterations of the competition.

The Google Landmark Recognition Challenge demonstration image.
Photo by Mick Haupt on Unsplash. Source.

The Competition

In this competition, you will be provided with a training dataset that will consist of images and the landmarks that are present in the images. You will have to train a model to predict the landmark that is present in the image by simply looking at the image. Along with the training dataset, you will also be provided with the test dataset, which will not be used for evaluating your final score but will only function as a representative of the final test dataset on which your submission will be evaluated. There will be a total of more than 81,000 classes that correspond to each landmark of the target variable in the dataset.

The solutions will be evaluated by the Global Average Precision(GAP) also known as the micro average precision(𝜇AP) metric over the entire test dataset. The run-time for the entire notebook, irrespective of whether a CPU is used or a GPU, should not exceed 12 hours. While the use of TPU will not be allowed during the submissions, they can still be used for training the models.

This competition is being held in conjunction with Landmark Retrieval Challenge.

Timelines

The competition began on 10th August 2021. And while the final submission deadline is on 1st October 2021, the deadline for entry into the competition and team merger is 24th September 2021. So far, there are already 119 competitors from 103 teams who have made 837 entries.

Prizes

Since this is a competition, there are obviously going to be prizes. Top 3 position holders will be a Kaggle merchandise of their choice. Although it may not sound like much as compared to other competitions on Kaggle, there is also another component to the prize.

The competition is a part of the Instance Level Recognition Workshop at the International Conference on Computer Vision, ICCV 2021. Competitors at the top of the leaderboard will be invited to give a talk at the workshop. Consequently, the winners of the completion will also have to submit their papers explaining their methods by 8th October 2021. The paper should at least be 2 pages long in the double-column format.

To be a part of the Google Landmark Recognition 2021 challenge, you just need to have a Kaggle Account. To know more about this challenge and participate in it, click here.

Good Luck!


Other Challenges

Kaggle, a subsidiary of Google is by far the biggest community of Data Science and Machine Learning practitioners. Kaggle regularly organizes competitions in various domains and on behalf of various organizations.

You can check out the blog on the Kaggle CHAII Research Challenge by Google, click here.

You can check out the blog on the Kaggle Gravitational Wave Detection challenge by G2Net, click here.

You can check out the blog on the Kaggle Volatility Forecasting challenge by Optiver, click here.