What technology significantly advanced computer vision before 2020?

Convolutional Neural Networks (CNNs) are a type of deep learning architecture that has had a transformative impact on the field of computer vision. Their structure is inspired by the human visual system and allows them to automatically and adaptively learn spatial hierarchies of features from images. This is achieved through layers that apply convolutional operations, which help in capturing local patterns and features in images, making CNNs particularly effective for tasks such as image classification, object detection, and segmentation.

Before the advent of CNNs, traditional machine learning methods like decision trees, support vector machines, and random forests were commonly used in computer vision. However, these methods often required manual feature extraction, which limited their effectiveness on complex visual tasks. The introduction of CNNs led to significant improvements in performance across various benchmarks and competitions, enabling much higher accuracy in applications such as facial recognition, image classification, and more.

Furthermore, large datasets and advances in computational power have allowed CNNs to be trained on vast amounts of data, further enhancing their capabilities in processing visual information. Overall, CNNs represent a pivotal advancement in computer vision, making them the correct choice in this context.