Basic Questions


I have a few general questions.

  1. The training dataset consists of images. So against what do I have to train the model from training data? Since there is no similarity index of some sort associated with images from training images, am I supposed to alter the images myself to test or develop a variable or something like that to compare, or use the reference images, like so. In general, how is the training set to be used?:confused:

  2. I can use any language and algorithm to solve the problem?

  3. I have to submit my solutions for Matching track only? Not necessarily for Descriptor track too?

I look forward for a prompt and descriptive answer ASAP.:worried:
Many thanks in advance.:slightly_smiling_face:

Hi Parth_B,

  1. Take a look at the “Getting Started” blog post for some ideas on how to use the training set.
  2. There are no restrictions on language or algorithm as long as you can generate submissions in the required format and are otherwise adhering to the competition rules.
  3. You may make submissions to one track or both tracks. It’s up to you.

I hope this helps.