Abstract | ||
---|---|---|
A novel variational autoencoder is developed to model images, as well as associated labels or captions. The Deep Generative Deconvolutional Network (DGDN) is used as a decoder of the latent image features, and a deep Convolutional Neural Network (CNN) is used as an image encoder; the CNN is used to approximate a distribution for the latent DGDN features/code. The latent code is also linked to generative models for labels (Bayesian support vector machine) or captions (recurrent neural network). When predicting a label/caption for a new image at test, averaging is performed across the distribution of latent codes; this is computationally efficient as a consequence of the learned CNN-based encoder. Since the framework is capable of modeling the image in the presence/absence of associated labels/captions, a new semi-supervised setting is manifested for CNN learning with images; the framework even allows unsupervised CNN learning, based on images alone. |
Year | Venue | DocType |
---|---|---|
2016 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 29 (NIPS 2016) | Conference |
Volume | ISSN | Citations |
29 | 1049-5258 | 45 |
PageRank | References | Authors |
1.33 | 21 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Pu, Yunchen | 1 | 57 | 1.97 |
Zhe Gan | 2 | 319 | 32.58 |
Ricardo Henao | 3 | 286 | 23.85 |
Xin Yuan | 4 | 383 | 27.60 |
Chunyuan Li | 5 | 467 | 33.86 |
andrew stevens | 6 | 58 | 2.26 |
L. Carin | 7 | 4603 | 339.36 |