Improving Bi-directional Generation between Different Modalities with Variational Autoencoders

نویسندگان

  • Masahiro Suzuki
  • Kotaro Nakayama
  • Yutaka Matsuo
چکیده

We investigate deep generative models that can exchange multiple modalities bi-directionally, e.g., generating images from corresponding texts and vice versa. A major approach to achieve this objective is to train a model that integrates all the information of different modalities into a joint representation and then to generate one modality from the corresponding other modality via this joint representation. We simply applied this approach to variational autoencoders (VAEs), which we call a joint multimodal variational autoencoder (JMVAE). However, we found that when this model attempts to generate a large dimensional modality missing at the input, the joint representation collapses and this modality cannot be generated successfully. Furthermore, we confirmed that this difficulty cannot be resolved even using a known solution. Therefore, in this study, we propose two models to prevent this difficulty: JMVAE-kl and JMVAE-h. Results of our experiments demonstrate that these methods can prevent the difficulty above and that they generate modalities bi-directionally with equal or higher likelihood than conventional VAE methods, which generate in only one direction. Moreover, we confirm that these methods can obtain the joint representation appropriately, so that they can generate various variations of modality by moving over the joint representation or changing the value of another modality.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Joint Multimodal Learning with Deep Generative Models

We investigate deep generative models that can exchange multiple modalities bidirectionally, e.g., generating images from corresponding texts and vice versa. Recently, some studies handle multiple modalities on deep generative models, such as variational autoencoders (VAEs). However, these models typically assume that modalities are forced to have a conditioned relation, i.e., we can only gener...

متن کامل

Hierarchical Variational Autoencoders for Music

In this work we develop recurrent variational autoencoders (VAEs) trained to reproduce short musical sequences and demonstrate their use as a creative device both via random sampling and data interpolation. Furthermore, by using a novel hierarchical decoder, we show that we are able to model long sequences with musical structure for both individual instruments and a three-piece band (lead, bass...

متن کامل

Deep Variational Inference Without Pixel-Wise Reconstruction

Variational autoencoders (VAEs), that are built upon deep neural networks have emerged as popular generative models in computer vision. Most of the work towards improving variational autoencoders has focused mainly on making the approximations to the posterior flexible and accurate, leading to tremendous progress. However, there have been limited efforts to replace pixel-wise reconstruction, wh...

متن کامل

Distributed and Cooperative Compressive Sensing Recovery Algorithm for Wireless Sensor Networks with Bi-directional Incremental Topology

Recently, the problem of compressive sensing (CS) has attracted lots of attention in the area of signal processing. So, much of the research in this field is being carried out in this issue. One of the applications where CS could be used is wireless sensor networks (WSNs). The structure of WSNs consists of many low power wireless sensors. This requires that any improved algorithm for this appli...

متن کامل

Semi-Amortized Variational Autoencoders

Amortized variational inference (AVI) replaces instance-specific local inference with a global inference network. While AVI has enabled efficient training of deep generative models such as variational autoencoders (VAE), recent empirical work suggests that inference networks can produce suboptimal variational parameters. We propose a hybrid approach, to use AVI to initialize the variational par...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • CoRR

دوره abs/1801.08702  شماره 

صفحات  -

تاریخ انتشار 2018