Related papers: Mean-Shifted Contrastive Loss for Anomaly Detectio…

Unsupervised learning methods for feature extraction are becoming more and more popular. We combine the popular contrastive learning method (prototypical contrastive learning) and the classic representation learning method (autoencoder) to…

Contrastive learning has become a key component of self-supervised learning approaches for computer vision. By learning to embed two augmented versions of the same image close to each other and to push the embeddings of different images…

Images with different resolutions are ubiquitous in public person re-identification (ReID) datasets and real-world scenes, it is thus crucial for a person ReID model to handle the image resolution variations for improving its generalization…

Detecting Out-of-Domain (OOD) or unknown intents from user queries is essential in a task-oriented dialog system. A key challenge of OOD detection is to learn discriminative semantic features. Traditional cross-entropy loss only focuses on…

This work studies the relationship between Contrastive Learning and Domain Adaptation from a theoretical perspective. The two standard contrastive losses, NT-Xent loss (Self-supervised) and Supervised Contrastive loss, are related to the…

Due to the intractability of characterizing everything that looks unlike the normal data, anomaly detection (AD) is traditionally treated as an unsupervised problem utilizing only normal samples. However, it has recently been found that…

Supervised deep learning-based methods yield accurate results for medical image segmentation. However, they require large labeled datasets for this, and obtaining them is a laborious task that requires clinical expertise.…

Recent progress in contrastive learning has revolutionized unsupervised representation learning. Concretely, multiple views (augmentations) from the same image are encouraged to map to the similar embeddings, while views from different…

Most anomaly detection (AD) models are learned using only normal samples in an unsupervised way, which may result in ambiguous decision boundary and insufficient discriminability. In fact, a few anomaly samples are often available in…

Traditional supervised learning methods are hitting a bottleneck because of their dependency on expensive manually labeled data and their weaknesses such as limited generalization ability and vulnerability to adversarial attacks. A…

Self-supervised representation learning can mitigate the limitations in recognition tasks with few manually labeled data but abundant unlabeled data---a common scenario in sound event research. In this work, we explore unsupervised…

Anomaly detection (AD) is a crucial machine learning task that aims to learn patterns from a set of normal training samples to identify abnormal samples in test data. Most existing AD studies assume that the training and test data are drawn…

To improve performance in visual feature representation from photos or videos for practical applications, we generally require large-scale human-annotated labeled data while training deep neural networks. However, the cost of gathering and…

Self-supervised contrastive learning heavily relies on the view variance brought by data augmentation, so that it can learn a view-invariant pre-trained representation. Beyond increasing the view variance for contrast, this work focuses on…

Semi-supervised anomaly detection, which aims to improve the anomaly detection performance by using a small amount of labeled anomaly data in addition to unlabeled data, has attracted attention. Existing semi-supervised approaches assume…

A key requirement for the success of supervised deep learning is a large labeled dataset - a condition that is difficult to meet in medical image analysis. Self-supervised learning (SSL) can help in this regard by providing a strategy to…

Predicting the future trajectories of surrounding vehicles based on their history trajectories is a critical task in autonomous driving. However, when small crafted perturbations are introduced to those history trajectories, the resulting…

Recent self-supervised contrastive methods have been able to produce impressive transferable visual representations by learning to be invariant to different data augmentations. However, these methods implicitly assume a particular set of…

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,…

One-class classification has been a prevailing method in building deep anomaly detection models under the assumption that a dataset consisting of normal samples is available. In practice, however, abnormal samples are often mixed in a…