Reviews: Introspective Classification with Convolutional Nets

The paper proposes a technique to improve the test accuracy of a discriminative model, by synthesizing additional negative input examples during the training process of the model. The negative example generation process has a Bayesian motivation, and is realized by "optimizing" for images (starting from random Gaussian noise) to maximize the probability of a given class label, a la DeepDream or Neural Artistic Style. These generated examples are added to the training set, and training is halted based on performance on a validation set. Experiments demonstrate that this procedure yields (very modest) improvements in test accuracy, and additionally provides some robustness against adversarial examples. The core idea is quite elegant, with an intuitive picture of using the "hard" negatives generated by the network to tighten the decision boundaries around the positive examples.