Skip to yearly menu bar Skip to main content


Poster

Introspective Classification with Convolutional Nets

Long Jin · Justin Lazarow · Zhuowen Tu

Pacific Ballroom #24

Keywords: [ Deep Learning ] [ Classification ]


Abstract:

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.

Live content is unavailable. Log in and register to view live content