How to implement a search engine-like function through a deep learning model?

[Shirui (Shirui Zhang)]

Assume that there are

• data set A (known sample information).
• data set B (unknown sample information).

What I want to achieve is:

1. Sort each sample of the data set A in a two-dimensional space according to a certain rule, that is, make it representable in two-dimensional coordinates.
   (According to the degree of similarity, correlation, etc. between the samples)

2. When a sample is extracted from the data set B and input to the deep learning model, the model can search in the data set A to obtain a sample (set) that has a certain correlation with the input sample.

How can I achieve it?

[MicPie (Michael)]

You can use that as a starting point:

Share your work here

We implemented a pretty amazing 2019 paper for image similarity / image retrieval using fast.ai. It’s of much lower complexity than other state-of-the-art methods (e.g. no triplet mining required), as fast to train as regular image classification DNNs, and has results which are on-par or better than the best previous published results. Repository: https://github.com/microsoft/computervision-recipes/tree/master/scenarios/similarity [imsim_example1]

but for the embedding you could only use 2D instead of more dimensions.

However, I am not sure if this can work with only 2D, but I would be happy to know if you find out.

[dhoa (Dien-Hoa)]

Not related to deeplearning but you can take a look at metric-learning http://contrib.scikit-learn.org/metric-learn/introduction.html . This kind of machine learning technique will try to reduce the distance of 2 similar samples and increase distance for different samples