How to go from a quick prototype to a production ready object detection system using active learning and Nvidia TLT.

Tired of labeling all your data? Learn more about how model predictions and embeddings can help you select the right data.

Startup@HSG featured an interview with Lightly co-founder Matthias in their monthly newsletter. It gives you a peek behind the curtain; how Lightly came to be and what's next for us.

This article provides a data preparation tool landscape for computer vision. The intention is to give an overview of the available solutions which machine learning engineers can use to build better models.

Deep learning's requirement of Big and Smart Data is currently met by labor-intensive processes of data labeling and cleaning. Self-supervised learning challenges this paradigm by enabling a more sustainable data pipeline.

‍A few personal thoughts on why self-supervised learning will have a strong impact on AI. From recent NLP to computer vision papers.

How we built a visual COVID-19 mask quality inspection prototype running on-device on an OpenMV-H7 board and the challenges on the way.

‍In few-shot learning, we train a model using only a few labeled examples. Learn how to train your classifier using transfer learning and a novel framework for sample selection.

‍Lots of interesting Deep learning applications rely on the use of complex architectures fueled by large datasets. However, when doing so, one ends up with lots of redundancies within the dataset.

This article provides a summary of popular optimizers used in computer vision, natural language processing, and machine learning in general.

In today’s globalized world, competition is becoming more and more intense. Products are getting better and cheaper. Can this race be won? How do you protect yourself from being disrupted by new, innovative products?

In Hollywood, video data segmentation has been done for decades. Simple tricks such as color keying with green screens can reduce work significantly. In late 2018 we worked on a video segmentation toolbox.

Are you curious about research areas such as active, self-supervised, and semi-supervised learning and how we can optimize datasets rather than optimizing deep learning models? You’re in good company, and this blog post will tell you all about it!

Customers are increasingly demanding smart products such as autonomous cars or home assistants. This leads to the expected growth of the AI market to over $100Bn by 2025 (image below). But what does it take to make a product smart?

In ML there is the saying garbage in, garbage out. But what does it really mean to have good or bad data? In this post, we will explore data redundancies in the training set of fashion-MNIST and how it affects test set accuracy.