Related papers: MD-Face: MoE-Enhanced Label-Free Disentangled Repr…

Although manipulating facial attributes by Generative Adversarial Networks (GANs) has been remarkably successful recently, there are still some challenges in explicit control of features such as pose, expression, lighting, etc. Recent…

This paper presents a novel approach for text/speech-driven animation of a photo-realistic head model based on blend-shape geometry, dynamic textures, and neural rendering. Training a VAE for geometry and texture yields a parametric model…

Facial Expression Recognition (FER) is an important task in computer vision and has wide applications in human-computer interaction, intelligent security, emotion analysis, and other fields. However, the limited size of FER datasets limits…

One of the biggest challenges for deep learning algorithms in medical image analysis is the indiscriminate mixing of image properties, e.g. artifacts and anatomy. These entangled image properties lead to a semantically redundant feature…

A feature learning task involves training models that are capable of inferring good representations (transformations of the original space) from input data alone. When working with limited or unlabelled data, and also when multiple visual…

Disentangled representation learning finds compact, independent and easy-to-interpret factors of the data. Learning such has been shown to require an inductive bias, which we explicitly encode in a generative model of images. Specifically,…

Conditional GANs are frequently used for manipulating the attributes of face images, such as expression, hairstyle, pose, or age. Even though the state-of-the-art models successfully modify the requested attributes, they simultaneously…

Deepfakes have recently raised significant trust issues and security concerns among the public. Compared to CNN face forgery detectors, ViT-based methods take advantage of the expressivity of transformers, achieving superior detection…

Masked Autoencoder (MAE) is a notable method for self-supervised pretraining in visual representation learning. It operates by randomly masking image patches and reconstructing these masked patches using the unmasked ones. A key limitation…

We propose an unsupervised, mid-level representation for a generative model of scenes. The representation is mid-level in that it is neither per-pixel nor per-image; rather, scenes are modeled as a collection of spatial, depth-ordered…

Disentangled visual representations have largely been studied with generative models such as Variational AutoEncoders (VAEs). While prior work has focused on generative methods for disentangled representation learning, these approaches do…

Despite the significant success in image-to-image translation and latent representation based facial attribute editing and expression synthesis, the existing approaches still have limitations in the sharpness of details, distinct image…

Masked autoencoder (MAE) is a promising self-supervised pre-training technique that can improve the representation learning of a neural network without human intervention. However, applying MAE directly to volumetric medical images poses…

Deep learning (DL) methods where interpretability is intrinsically considered as part of the model are required to better understand the relationship of clinical and imaging-based attributes with DL outcomes, thus facilitating their use in…

We propose TopDis (Topological Disentanglement), a method for learning disentangled representations via adding a multi-scale topological loss term. Disentanglement is a crucial property of data representations substantial for the…

Disentangled representation learning is one of the major goals of deep learning, and is a key step for achieving explainable and generalizable models. A well-defined theoretical guarantee still lacks for the VAE-based unsupervised methods,…

The performance of a convolutional neural network (CNN) based face recognition model largely relies on the richness of labelled training data. Collecting a training set with large variations of a face identity under different poses and…

Advancement in speech technology has brought convenience to our life. However, the concern is on the rise as speech signal contains multiple personal attributes, which would lead to either sensitive information leakage or bias toward…

Disentangled representations enable models to separate factors of variation that are shared across experimental conditions from those that are condition-specific. This separation is essential in domains such as biomedical data analysis,…

We present an autoencoder that leverages learned representations to better measure similarities in data space. By combining a variational autoencoder with a generative adversarial network we can use learned feature representations in the…