Machine Learning Times
Machine Learning Times
AI Success Depends On How You Choose This One Number
 Originally published in Forbes, March 25, 2024. To do...
Elon Musk Predicts Artificial General Intelligence In 2 Years. Here’s Why That’s Hype
 Originally published in Forbes, April 10, 2024 When OpenAI’s...
Survey: Machine Learning Projects Still Routinely Fail to Deploy
 Originally published in KDnuggets. Eric Siegel highlights the chronic...
Three Best Practices for Unilever’s Global Analytics Initiatives
    This article from Morgan Vawter, Global Vice...

3 years ago
How Image Search Works at Dropbox

Originally posted in, May 11, 2021

Photos are among the most common types of files in Dropbox, but searching for them by filename is even less productive than it is for text-based files.  When you’re looking for that photo from a picnic a few years ago, you surely don’t remember that the filename set by your camera was 2017-07-04 12.37.54.jpg.

Instead, you look at individual photos, or thumbnails of them, and try to identify objects or aspects that match what you’re searching for—whether that’s to recover a photo you’ve stored, or perhaps discover the perfect shot for a new campaign in your company’s archives.  Wouldn’t it be great if Dropbox could pore through all those images for you instead, and call out those which best match a few descriptive words that you dictated? That’s pretty much what our image search does.

In this post we’ll describe the core idea behind our image content search method, based on techniques from machine learning, then discuss how we built a performant implementation on Dropbox’s existing search infrastructure.

1. Our approach

Here’s a simple way to state the image search problem: find a relevance function that takes a (text) query q and an image j, and returns a relevance score s indicating how well the image matches the query.

s = f(q, j)

Given this function, when a user does a search we run it on all their images and return those that produce a score above a threshold, sorted by their scores.  We build this function using two key developments in machine learning: accurate image classification and word vectors.

To continue reading this article, click here.

2 thoughts on “How Image Search Works at Dropbox

  1. Interesting strategy, I had no idea. With this option, searching for photographs has gotten considerably simpler. Sometimes it seems difficult to post an image. However, it depends on the resource that is used. With the resource database images you may select the image’s extension and do a complete download of it. The same is true for blogs and forums.


Leave a Reply