Title
Generative-Discriminative Variational Model for Visual Recognition.
Abstract
The paradigm shift from shallow classifiers with hand-crafted features to end-to-end trainable deep learning models has shown significant improvements on supervised learning tasks. Despite the promising power of deep neural networks (DNN), how to alleviate overfitting during training has been a research topic of interest. In this paper, we present a Generative-Discriminative Variational Model (GDVM) for visual classification, in which we introduce a latent variable inferred from inputs for exhibiting generative abilities towards prediction. In other words, our GDVM casts the supervised learning task as a generative learning process, with data discrimination to be jointly exploited for improved classification. In our experiments, we consider the tasks of multi-class classification, multi-label classification, and zero-shot learning. We show that our GDVM performs favorably against the baselines or recent generative DNN models.
Year
Venue
Field
2017
arXiv: Learning
Semi-supervised learning,Pattern recognition,Computer science,Deep belief network,Supervised learning,Artificial intelligence,Data discrimination,Deep learning,Overfitting,Discriminative model,Machine learning,Generative model
DocType
Volume
Citations 
Journal
abs/1706.02295
0
PageRank 
References 
Authors
0.34
15
3
Name
Order
Citations
PageRank
Chih-Kuan Yeh112.05
Yao-Hung Hubert Tsai253.19
Yu-Chiang Frank Wang391461.63