Abstract. . To detect unknown classes while still generalizing
to new instances of existing classes, we introduce a dataset augmentation
technique that we call counterfactual image generation. Our approach,
based on generative adversarial networks, generates examples that are
close to training set examples yet do not belong to any training category.
By augmenting training with examples generated by this optimization,
we can reformulate open set recognition as classification with one additional class, which includes the set of novel and unknown examples.
Our approach outperforms existing open set recognition algorithms on a
selection of image classification tasks.