Video streams are so rich, and video workloads are so sophisticated, that we may now expect video ML to supply many simultaneous insights and transformations. It will be increasingly common to need video segmentation, object and motion recognition, SLAM, 3D […]
Bias is a critical challenge in predictive and generative AI that involves images of humans. People have a variety of body shapes, skin tones and other features that can be challenging to represent completely in training data. Without attention to […]
In this talk, we will explore methods to transform large deep neural network (DNN) models into effective compact models. The transformation process that we focus on—from large to compact DNN form—is referred to as pruning. Pruning involves the removal of […]
An unforeseen change in the input data is called “drift,” and may impact the accuracy of machine learning models. In this talk, we present a novel scheme for diagnosing data drift in the input streams of image classification neural networks. […]
In what format can an AI system best present what it “sees” in a visual scene to help robots accomplish tasks? This question has been a long-standing challenge for computer scientists and robotics engineers. In this presentation, we will provide […]
With the boom in tools for developing, monitoring and maintaining ML models, data science teams have many options to choose from. Proprietary tools provided by cloud service providers are enticing, but teams may fear being locked in—and may worry that […]
One of the main challenges when deploying computer vision models to the edge is optimizing the model for speed, memory and energy consumption. In this talk, we’ll provide a comprehensive survey of model compression approaches, which are crucial for harnessing […]
Offloading visual processing to a hardware accelerator has many advantages for embedded vision systems. Decoupling hardware and software removes barriers to innovation and shortens time to market. Using hardware acceleration, embedded vision system manufacturers can integrate and deploy new components […]
Generative adversarial networks, or GANs, are widely used to create amazing “fake” images and realistic, synthetic training data. And yet, despite their name, mainstream GANs generate only the examples that are easiest to find, rather than the promised adversaries, which […]
Selecting the appropriate type of image sensor is essential for reliable and accurate performance of vision applications. In this talk, we explore some of the critical factors to consider in selecting an image sensor, including shutter type, dynamic range, resolution […]
