Related papers: Neural Audio Fingerprint for High-specific Audio R…

Fine-tuning a pre-trained language model via the contrastive learning framework with a large amount of unlabeled sentences or labeled sentence pairs is a common way to obtain high-quality sentence representations. Although the contrastive…

We present a method for audio denoising that combines processing done in both the time domain and the time-frequency domain. Given a noisy audio clip, the method trains a deep neural network to fit this signal. Since the fitting is only…

Humans do not acquire perceptual abilities in the way we train machines. While machine learning algorithms typically operate on large collections of randomly-chosen, explicitly-labeled examples, human acquisition relies more heavily on…

We present a novel semi-supervised semantic segmentation method which jointly achieves two desiderata of segmentation model regularities: the label-space consistency property between image augmentations and the feature-space contrastive…

Ultrasound denoising is essential for mitigating speckle-induced degradations, thereby enhancing image quality and improving diagnostic reliability. Nevertheless, because speckle patterns inherently encode both texture and fine anatomical…

Due to the lack of target speech annotations in real-recorded far-field conversational datasets, speech enhancement (SE) models are typically trained on simulated data. However, the trained models often perform poorly in real-world…

Detecting critical transitions in complex, noisy time-series data is a fundamental challenge across science and engineering. Such transitions may be anticipated by the emergence of a low-dimensional order parameter, whose signature is often…

Contrastive learning, which aims to capture general representation from unlabeled images to initialize the medical analysis models, has been proven effective in alleviating the high demand for expensive annotations. Current methods mainly…

Separating audio mixtures into individual instrument tracks has been a long standing challenging task. We introduce a novel weakly supervised audio source separation approach based on deep adversarial learning. Specifically, our loss…

Inspired by the idea of Positive-incentive Noise (Pi-Noise or $\pi$-Noise) that aims at learning the reliable noise beneficial to tasks, we scientifically investigate the connection between contrastive learning and $\pi$-noise in this…

Obtaining labelled ECG data for developing supervised models is challenging. Contrastive learning (CL) has emerged as a promising pretraining approach that enables effective transfer learning with limited labelled data. However, existing CL…

Contrastive learning-based recommendation algorithms have significantly advanced the field of self-supervised recommendation, particularly with BPR as a representative ranking prediction task that dominates implicit collaborative filtering.…

With the onset of the COVID-19 pandemic, ultrasound has emerged as an effective tool for bedside monitoring of patients. Due to this, a large amount of lung ultrasound scans have been made available which can be used for AI based diagnosis…

We present a self-supervised learning method to learn audio and video representations. Prior work uses the natural correspondence between audio and video to define a standard cross-modal instance discrimination task, where a model is…

Contrastive learning has become pivotal in unsupervised representation learning, with frameworks like Momentum Contrast (MoCo) effectively utilizing large negative sample sets to extract discriminative features. However, traditional…

We propose a self-supervised learning method using multiple sampling strategies to obtain general-purpose audio representation. Multiple sampling strategies are used in the proposed method to construct contrastive losses from different…

auDeep is a Python toolkit for deep unsupervised representation learning from acoustic data. It is based on a recurrent sequence to sequence autoencoder approach which can learn representations of time series data by taking into account…

Learning segmentation from noisy labels is an important task for medical image analysis due to the difficulty in acquiring highquality annotations. Most existing methods neglect the pixel correlation and structural prior in segmentation,…

Supervised learning of deep neural networks heavily relies on large-scale datasets annotated by high-quality labels. In contrast, mislabeled samples can significantly degrade the generalization of models and result in memorizing samples,…

We address the problem of few-shot semantic segmentation (FSS), which aims to segment novel class objects in a target image with a few annotated samples. Though recent advances have been made by incorporating prototype-based metric…