What Makes Transfer Learning Work For Medical Images — Transfer learning is a common technique to transfer knowledge from one domain to another. It might be easy to understand why using knowledge from one dataset to a different dataset with similar characteristics might work. But what makes transfer learning works for medical images? Medical images have totally different characteristics…

Introducing an Automatic Pipeline for Training, Tracing, and Comparing Machine Learning Experiments — Let’s imagine the following scenario: you get a new project to work on. For this project, you need to develop a machine learning model, which will require running and training several experiments. Each experiment might take several hours or even days and needs to be tracked. You have your own…

A Gentle Introduction to JSON Schema In Python — Imagine the following scenario: you and your teammate are working on a new feature. Your part is to create a JSON with some results and send it to your teammate. Her part is to take this JSON, parse it and save it in the database. You verbally agreed on what…

Two Advantages in Using GANs for Medical Data — Supervised deep learning methods require a large amount of data which might be hard to obtain, especially in the medical domain. One reason is that it is private data that we can’t always get, use and share. The second reason is the difficulty to obtain labels for this data. Expert…

Analyzing Geometric Objects Directly in SQL Without Additional Python Code — When we talk about the input and output of Computer Vision algorithms we mainly talk about two things — the images and the annotations. While the images are mostly stored in cloud storage, the annotations have a wider range of storing options. …

How do I evaluate my Active Learning results? — In my previous posts, I described what is Active Learning (introduction to Active Learning and the main approaches) and how one can implement such a pipeline in a simple and generic way (architecture for Active Learning pipeline). This post is based on a talk I gave at Reversim Summit 2021…

Simple, modular, and generic architecture for active learning — In my previous post, I gave a short introduction to the theory and methods of active learning. The next step in the Active Learning journey is the implementation. In this post, I will share my journey towards a complete automated active learning pipeline. Step 1 — Motivation to implement At first, like other motivated algorithm developers…

A short introduction to Active Learning for Computer Vision — Deep learning (DL) models are the most common methods for many tasks in computer vision. DL achieves tremendous results by using a huge amount of labeled data. …