A new machine learning strategy that could enhance computer vision

Researchers from the Universitat Autonoma de Barcelona, Carnegie Mellon University and International Institute of Information Technology, Hyderabad, India, have developed a technique that could allow deep learning algorithms to learn the visual features of images in a self-supervised fashion, without the need for annotations by human researchers. To achieve remarkable results in computer vision tasks, deep learning algorithms need to be trained on large-scale annotated datasets that include extensive information about every image. However, collecting and manually annotating these images requires huge amounts of time, resources, and human effort. "We aim to give computers the capability to read and understand textual information in any type of image in the real-world," says Dimosthenis Karatzas, one of the researchers who carried out the study, in an interview with Tech Xplore. Humans use textual information to interpret all situations presented to them, as well as to describe what is happening around them or in a particular image.