Timezone: »

Introspective Classification with Convolutional Nets
Long Jin · Justin Lazarow · Zhuowen Tu

Mon Dec 04 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #24 #None

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.

Author Information

Long Jin (University of California San Diego)
Justin Lazarow (UC San Diego)
Zhuowen Tu (University of California, San Diego)