Related papers: A Co-training Approach for Noisy Time Series Learn…

The remarkable progress in deep learning (DL) showcases outstanding results in various computer vision tasks. However, adaptation to real-time variations in data distributions remains an important challenge. Test-Time Training (TTT) was…

Change Point Detection (CPD) methods identify the times associated with changes in the trends and properties of time series data in order to describe the underlying behaviour of the system. For instance, detecting the changes and anomalies…

The decomposition of a stochastic time series into three component series representing a dual signal - namely, the mean and dispersion - while isolating noise is presented. The decomposition is performed by applying machine learning…

In step with the digitalization of transportation, we are witnessing a growing range of path-based smart-city applications, e.g., travel-time estimation and travel path ranking. A temporal path(TP) that includes temporal information, e.g.,…

Contrastive learning methods have shown an impressive ability to learn meaningful representations for image or time series classification. However, these methods are less effective for time series forecasting, as optimization of instance…

Self-supervised pre-training methods based on contrastive learning or regression tasks can utilize more unlabeled data to improve the performance of automatic speech recognition (ASR). However, the robustness impact of combining the two…

Contrastive self-supervised learning methods famously produce high quality transferable representations by learning invariances to different data augmentations. Invariances established during pre-training can be interpreted as strong…

Data efficient voice cloning aims at synthesizing target speaker's voice with only a few enrollment samples at hand. To this end, speaker adaptation and speaker encoding are two typical methods based on base model trained from multiple…

Time series anomaly detection (TSAD) plays a vital role in many industrial applications. While contrastive learning has gained momentum in the time series domain for its prowess in extracting meaningful representations from unlabeled data,…

Current vision systems are trained on huge datasets, and these datasets come with costs: curation is expensive, they inherit human biases, and there are concerns over privacy and usage rights. To counter these costs, interest has surged in…

Despite extensive research, time series classification and forecasting on noisy data remain highly challenging. The main difficulties lie in finding suitable mathematical concepts to describe time series and effectively separate noise from…

Deep learning with noisy labels is challenging as deep neural networks have the high capacity to memorize the noisy labels. In this paper, we propose a learning algorithm called Co-matching, which balances the consistency and divergence…

State-of-the art vision models can achieve superhuman performance on image classification tasks when testing and training data come from the same distribution. However, when models are tested on corrupted images (e.g. due to scale changes,…

A steady momentum of innovations and breakthroughs has convincingly pushed the limits of unsupervised image representation learning. Compared to static 2D images, video has one more dimension (time). The inherent supervision existing in…

Unsupervised representation learning has recently received lots of interest due to its powerful generalizability through effectively leveraging large-scale unlabeled data. There are two prevalent approaches for this, contrastive learning…

The lack of labeled data is a key challenge for learning useful representation from time series data. However, an unsupervised representation framework that is capable of producing high quality representations could be of great value. It is…

Recent advances in audio-visual representation learning have shown the value of combining contrastive alignment with masked reconstruction. However, jointly optimizing these objectives in a single forward pass forces the contrastive branch…

Recently, contrastive learning attracts increasing interests in neural text generation as a new solution to alleviate the exposure bias problem. It introduces a sequence-level training signal which is crucial to generation tasks that always…

The instance discrimination paradigm has become dominant in unsupervised learning. It always adopts a teacher-student framework, in which the teacher provides embedded knowledge as a supervision signal for the student. The student learns…

Unsupervised representation learning approaches aim to learn discriminative feature representations from unlabeled data, without the requirement of annotating every sample. Enabling unsupervised representation learning is extremely crucial…