Object recognition neural network training using multiple data sources

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an object recognition neural network using multiple data sources. One of the methods includes receiving training data that includes a plurality of training images from a first source and images from a second source. For each training image, contrast equalization is applied to generate a modified image, which is processed using the neural network to generate an object recognition output, and a loss is determined based on errors.