ssl blogpost fig2

On the Stepwise Nature of Self-Supervised Learning

Figure 1: stepwise behavior in self-supervised learning. When training common SSL algorithms, we find that the loss descends in a stepwise fashion (top left) and the learned embeddings iteratively increase in dimensionality (bottom left). Direct visualization of embeddings (right; top three PCA directions shown) confirms that embeddings are initially collapsed to a point, which then …

What is a knowledge worker and what do they do?

Knowledge workers, typically those with advanced training and years of experience, have become a valuable asset for companies worldwide. Businesses lean on these people who “think for a living” to drive innovation, solve problems and manage personnel. Yet, empowering knowledge workers to stay productive can be a constant challenge. Too often, these skilled workers get …

hero

Modular visual question answering via code generation

Posted by Sanjay Subramanian, PhD student, UC Berkeley, and Arsha Nagrani, Research Scientist, Google Research, Perception Team Visual question answering (VQA) is a machine learning task that requires a model to answer a question about an image or a set of images. Conventional VQA approaches need a large amount of labeled training data consisting of …

1 KBTG Labs.max 1000x1000 1

Formulating a more effective way to identify vehicle damage with Explainable AI

Turning images of damaged vehicles into accurate claims information is critical for insurance agencies. For that reason, KASIKORN Business-Technology Group (KBTG) Labs, a leading tech company in Thailand, is using Machine learning (ML) technology to help speed up this process, and ensure the accuracy of every claim. KBTG worked with Muang Thai Insurance PCL (MTI), …