Introspective Classification with Convolutional Nets
This work addresses the need for more robust and versatile neural networks in computer vision, though it appears incremental as it builds on existing CNN architectures.
The paper tackles the problem of enhancing convolutional neural networks by integrating generative capabilities, resulting in improved classification performance on benchmark datasets like MNIST, CIFAR-10, and SVHN.
We propose introspective convolutional networks (ICN) that emphasize the importance of having convolutional neural networks empowered with generative capabilities. We employ a reclassification-by-synthesis algorithm to perform training using a formulation stemmed from the Bayes theory. Our ICN tries to iteratively: (1) synthesize pseudo-negative samples; and (2) enhance itself by improving the classification. The single CNN classifier learned is at the same time generative --- being able to directly synthesize new samples within its own discriminative model. We conduct experiments on benchmark datasets including MNIST, CIFAR-10, and SVHN using state-of-the-art CNN architectures, and observe improved classification results.