What’s in a name? In the last section, we did several things: Provided a definition and background for contrastive representation learning Set up a dataset for a contrastive learning task Modified a model’s architecture to produce embeddings instead of classifications Wrote a trainer for the model using a variety of…

Turns out, telling things apart is a good way to understand the world Nobody likes labels. Specifically with regards to machine learning, the modus operandi of most models is to take in batches of data elements and their associated labels (“cat”, “road pixel”, “adjective” etc.) …

Fine-tuning a deep learning model for building footprints to be used for automatically counting new buildings in temporal panchromatic imagery Change detection is an extremely important area of remote sensing. It helps us understand, given imagery or radar scans of given locations, what meaningful semantic changes occurred in categories of…

Visualizing Pytorch Models with Tensorboard’s Embedding Viewer — In many ways, deep learning has brought upon a new age of descriptive, predictive, and generative modeling to many dozens of industries and research areas. In light of its usefulness its also found a wealth of popularity, and with popularity often comes simplification. The most common simplification is that the…

To many people’s dismay, there is still a giant wealth of paper documents floating out there in the world. Tucked into corner drawers, stashed in filing cabinets, overflowing from cubicle shelves — these are headaches to keep track of, keep updated, and just store. What if there existed a system…

How much text and audio content have you consumed this week? Maybe you read a news article on “Flattening the Curve” and watched a Youtube video to understand what that really means? Maybe you finally looked up the lyrics to your favorite song and realized it was actually talking about…

With all the discussions about the dangers and ethics around emerging artificial intelligence technologies, we sometimes forget all the good that AI is doing in the world. For this article, I’ll outline some of the work we are doing at Esri using AI for improving disaster response. We will ultimately…

Visual attention is so much a part of everyday life that most people never stop to think about why, or how, it happens. Focusing on the road while you’re driving, glancing at the food on your plate before you take a bite, looking at the text instead of the sidebars…

In predicting real world events, there’s two main types of outcomes we can use to cover most questions. If the outcome we’re trying to predict can take on any and every value in some interval (such as temperature, bodyweight, speed, calories) then we say the outcome is continuous. …