Requirement of matching algorithm

for tack1, we are required to submit the matched results.
is there any requirement for the matching algorithm. e.g.

  • only KNN retrieval (like track 2) is allowed

  • if we assume one-to-one match (i.e. one reference is only match to one query), there are many post-processing tricks we can use for bipartite match. Are such assumptions and methods allowed?

  • model the matcher as another deep network

  • assume match is random, i.e. if we randomly divide the reference images into groups (buckets) of m images each, number of matches found for each group is fairly constant

  • "There are a total of 50K query images, of which 10K have matches in the reference set,
    while the remaining 40K do not. " Use this prior knowledge in our modeling. But do stage2 images follow the same rule?

  • train classifier to identify disractor images?

  • use meata data like image size, jpg header, etc

  • check for jpg recompression artifacts or other image forensics methods,

"This means that even if the dataset had a single query image and a single reference image, the score of the image pair would be the same. "

Hi hengcherkeng – thanks for the questions. I recommend you take a close look at the “Rules on Data Use” section of the Problem Description.

As wenhaowang points out, your algorithm must treat each new image of the reference set independently and without any interaction with other reference images.

I hope this helps. After reading through the rules, feel free to let us know if any question remains unanswered.