Related papers: Joint Generative-Contrastive Representation Learni…

Training effective Generative Adversarial Networks (GANs) requires large amounts of training data, without which the trained models are usually sub-optimal with discriminator over-fitting. Several prior studies address this issue by…

A study is presented in which a contrastive learning approach is used to extract low-dimensional representations of the acoustic environment from single-channel, reverberant speech signals. Convolution of room impulse responses (RIRs) with…

This paper presents a deep learning-based approach for the spatio-temporal reconstruction of sound fields using Generative Adversarial Networks (GANs). The method utilises a plane wave basis and learns the underlying statistical…

In this paper, we introduce a contrastive learning framework for keypoint detection (CoKe). Keypoint detection differs from other visual tasks where contrastive learning has been applied because the input is a set of images in which…

This study delves into the application of Generative Adversarial Networks (GANs) within the context of imbalanced datasets. Our primary aim is to enhance the performance and stability of GANs in such datasets. In pursuit of this objective,…

Representation learning is a fundamental aspect of modern artificial intelligence, driving substantial improvements across diverse applications. While selfsupervised contrastive learning has led to significant advancements in fields like…

We present a new method for improving the performances of variational autoencoder (VAE). In addition to enforcing the deep feature consistent principle thus ensuring the VAE output and its corresponding input images to have similar deep…

Deep generative models have been used in recent years to learn coherent latent representations in order to synthesize high-quality images. In this work, we propose a neural network to learn a generative model for sampling consistent indoor…

Self-supervised learning, especially contrastive learning, has made an outstanding contribution to the development of many deep learning research fields. Recently, researchers in the acoustic signal processing field noticed its success and…

Self-supervised learning (SSL) has become prevalent for learning representations in computer vision. Notably, SSL exploits contrastive learning to encourage visual representations to be invariant under various image transformations. The…

Machine anomalous sound detection (ASD) is a valuable technique across various applications. However, its generalization performance is often limited due to challenges in data collection and the complexity of acoustic environments. Inspired…

Recently, self-supervised representation learning relying on vast amounts of unlabeled data has been explored as a pre-training method for autonomous driving. However, directly applying popular contrastive or generative methods to this…

We present variational generative adversarial networks, a general learning framework that combines a variational auto-encoder with a generative adversarial network, for synthesizing images in fine-grained categories, such as faces of a…

We propose GC-VASE, a graph convolutional-based variational autoencoder that leverages contrastive learning for subject representation learning from EEG data. Our method successfully learns robust subject-specific latent representations…

As the labor force decreases, the demand for labor-saving automatic anomalous sound detection technology that conducts maintenance of industrial equipment has grown. Conventional approaches detect anomalies based on the reconstruction…

Mainstream 3D representation learning approaches are built upon contrastive or generative modeling pretext tasks, where great improvements in performance on various downstream tasks have been achieved. However, we find these two paradigms…

We propose using an adversarial autoencoder (AAE) to replace generative adversarial network (GAN) in the private aggregation of teacher ensembles (PATE), a solution for ensuring differential privacy in speech applications. The AAE…

Despite recent progress in video and language representation learning, the weak or sparse correspondence between the two modalities remains a bottleneck in the area. Most video-language models are trained via pair-level loss to predict…

Existing audio analysis methods generally first transform the audio stream to spectrogram, and then feed it into CNN for further analysis. A standard CNN recognizes specific visual patterns over feature map, then pools for high-level…

Recently, pre-trained transformer-based models have achieved great success in the task of definition generation (DG). However, previous encoder-decoder models lack effective representation learning to contain full semantic components of the…