| |
 |
| Paper: |
“You Might Also Like These Images”: Unsupervised Affine-Transformation-Independent Representation Learning for the ALMA Science Archive |
| Volume: |
541, ADASS XXXIII |
| Page: |
173 |
| Authors: |
Felix Stoehr |
| DOI: |
10.26624/NVGP3776 |
| Abstract: |
With the exponential growth of the amount of astronomical data with
time, finding the needles in the haystack is getting increasingly difficult. The next
frontier for science archives is to also allow searches on the content of the observations themselves. As a step into this direction, we have implemented a prototype of a
recommender system for the ALMA Science Archive (ASA). We use self-supervised affine-transformation-independent representation learning of source morphologies for
the similarity estimation through contrastive learning with a deep neural network. Once
the neural network is trained, the feature vectors for all images - both for continuum
images and for peak-flux images of data cubes - are evaluated. In a next step, we compute the similarity matrix holding for each image the corresponding 1000 most similar
images, ordered by their pairwise similarity. A kd-tree is used to speed up that computation from O(N2) to O(Nlog(N)). Our prototype interface then shows the most-similar
images of which the archival researcher can select the most interesting ones. When
they do select an image on the interface, we instantaneously re-compute the combined
similarity of all the selected images and reorder the displayed remaining images accordingly. Each selection thus further refines the similarity display. Finally, we use k-means
clustering on the feature vectors to provide selectable `source morphology categories’
for a quick-select option. We conclude from the prototype that an image similarity
interface can be a valuable asset to science archives. |
|
|
|
|
|
