Related papers: VQ-Style: Disentangling Style and Content in Motio…

Existing neural style transfer researches have studied to match statistical information between the deep features of content and style images, which were extracted by a pre-trained VGG, and achieved significant improvement in synthesizing…

In this work we address disentanglement of style and content in speech signals. We propose a fully convolutional variational autoencoder employing two encoders: a content encoder and a style encoder. To foster disentanglement, we propose…

In this paper we introduce learnable lattice vector quantization and demonstrate its effectiveness for learning discrete representations. Our method, termed LL-VQ-VAE, replaces the vector quantization layer in VQ-VAE with lattice-based…

The rapid growth of visual data under stringent storage and bandwidth constraints makes extremely low-bitrate image compression increasingly important. While Vector Quantization (VQ) offers strong structural fidelity, existing methods lack…

As an increasing amount of image and video content will be analyzed by machines, there is demand for a new codec paradigm that is capable of compressing visual input primarily for the purpose of computer vision inference, while secondarily…

Many methods have been proposed to solve the domain adaptation problem recently. However, the success of them implicitly funds on the assumption that the information of domains are fully transferrable. If the assumption is not satisfied,…

Image-to-image translation aims to learn the mapping between two visual domains. There are two main challenges for many applications: 1) the lack of aligned training pairs and 2) multiple possible outputs from a single input image. In this…

Cross-domain disentanglement is the problem of learning representations partitioned into domain-invariant and domain-specific representations, which is a key to successful domain transfer or measuring semantic distance between two domains.…

Controlling the style of natural language by disentangling the latent space is an important step towards interpretable machine learning. After the latent space is disentangled, the style of a sentence can be transformed by tuning the style…

Current image-to-image translation methods formulate the task with conditional generation models, leading to learning only the recolorization or regional changes as being constrained by the rich structural information provided by the…

Scene text images contain not only style information (font, background) but also content information (character, texture). Different scene text tasks need different information, but previous representation learning methods use tightly…

Image generative models can learn the distributions of the training data and consequently generate examples by sampling from these distributions. However, when the training dataset is corrupted with outliers, generative models will likely…

A recent spate of state-of-the-art semi- and un-supervised solutions disentangle and encode image "content" into a spatial tensor and image appearance or "style" into a vector, to achieve good performance in spatially equivariant tasks…

Vector Quantized Variational AutoEncoders (VQ-VAEs) are designed to compress a continuous input to a discrete latent space and reconstruct it with minimal distortion. They operate by maintaining a set of vectors -- often referred to as the…

Vector Quantized Variational Autoencoders (VQ-VAEs) are fundamental to modern generative modeling, yet they often suffer from training instability and "codebook collapse" due to the inherent coupling of representation learning and discrete…

Under limited data setting, GANs often struggle to navigate and effectively exploit the input latent space. Consequently, images generated from adjacent variables in a sparse input latent space may exhibit significant discrepancies in…

We build on the Visual Autoregressive Modeling (VAR) framework and formulate style transfer as conditional discrete sequence modeling in a learned latent space. Images are decomposed into multi-scale representations and tokenized into…

Generative models that learn disentangled representations for different factors of variation in an image can be very useful for targeted data augmentation. By sampling from the disentangled latent subspace of interest, we can efficiently…

For speaker recognition, it is difficult to extract an accurate speaker representation from speech because of its mixture of speaker traits and content. This paper proposes a disentanglement framework that simultaneously models speaker…

Recognizing elementary underlying concepts from observations (disentanglement) and generating novel combinations of these concepts (compositional generalization) are fundamental abilities for humans to support rapid knowledge learning and…