Related papers: Disentanglement for Discriminative Visual Recognit…

Deep learning models exhibit limited generalizability across different domains. Specifically, transferring knowledge from available entangled domain features(source/target domain) and categorical features to new unseen categorical features…

Latent space-based facial attribute editing methods have gained popularity in applications such as digital entertainment, virtual avatar creation, and human-computer interaction systems due to their potential for efficient and flexible…

This work presents a framework based on feature disentanglement to learn speaker embeddings that are robust to environmental variations. Our framework utilises an auto-encoder as a disentangler, dividing the input speaker embedding into…

Facial Attribute Classification (FAC) has attracted increasing attention in computer vision and pattern recognition. However, state-of-the-art FAC methods perform face detection/alignment and FAC independently. The inherent dependencies…

The accuracy of facial expression recognition is typically affected by the following factors: high similarities across different expressions, disturbing factors, and micro-facial movement of rapid and subtle changes. One potentially viable…

We aim to separate the generative factors of data into two latent vectors in a variational autoencoder. One vector captures class factors relevant to target classification tasks, while the other vector captures style factors relevant to the…

Latent representations are critical for the performance and robustness of machine learning models, as they encode the essential features of data in a compact and informative manner. However, in vision tasks, these representations are often…

We present a framework for learning disentangled and interpretable jointly continuous and discrete representations in an unsupervised manner. By augmenting the continuous latent distribution of variational autoencoders with a relaxed…

Disentangling the underlying feature attributes within an image with no prior supervision is a challenging task. Models that can disentangle attributes well provide greater interpretability and control. In this paper, we propose a…

Deep learning techniques have demonstrated significant capacity in modeling some of the most challenging real world problems of high complexity. Despite the popularity of deep models, we still strive to better understand the underlying…

The deployment of machine listening algorithms in real-life applications is often impeded by a domain shift caused for instance by different microphone characteristics. In this paper, we propose a novel domain adaptation strategy based on…

Unsupervised disentangled representation learning is a long-standing problem in computer vision. This work proposes a novel framework for performing image clustering from deep embeddings by combining instance-level contrastive learning with…

Effective expression feature representations generated by a triplet-based deep metric learning are highly advantageous for facial expression recognition (FER). The performance of triplet-based deep metric learning is contingent upon…

Tensor-based multi-view clustering has recently received significant attention due to its exceptional ability to explore cross-view high-order correlations. However, most existing methods still encounter some limitations. (1) Most of them…

Current autoencoder-based disentangled representation learning methods achieve disentanglement by penalizing the (aggregate) posterior to encourage statistical independence of the latent factors. This approach introduces a trade-off between…

In this work, we address activity-biometrics, which involves identifying individuals across diverse set of activities. Unlike traditional person identification, this setting introduces additional challenges as identity cues become entangled…

Disentangled representation learning (DRL) aims to break down observed data into core intrinsic factors for a profound understanding of the data. In real-world scenarios, manually defining and labeling these factors are non-trivial, making…

Deep learning based approaches have been dominating the face recognition field due to the significant performance improvement they have provided on the challenging wild datasets. These approaches have been extensively tested on such…

Machine learning systems produce biased results towards certain demographic groups, known as the fairness problem. Recent approaches to tackle this problem learn a latent code (i.e., representation) through disentangled representation…

Deep learning (DL) applied to a device's radio-frequency fingerprint~(RFF) has attracted significant attention in physical-layer authentication due to its extraordinary classification performance. Conventional DL-RFF techniques are trained…