相关论文: Embedding contrastive unsupervised features to clu…

Training a classifier on web-crawled data demands learning algorithms that are robust to annotation errors and irrelevant examples. This paper builds upon the recent empirical observation that applying unsupervised contrastive learning to…

Unsupervised out-of-distribution (OOD) Detection aims to separate the samples falling outside the distribution of training data without label information. Among numerous branches, contrastive learning has shown its excellent capability of…

Unsupervised out-of-distribution (OOD) detection aims to identify out-of-domain data by learning only from unlabeled In-Distribution (ID) training samples, which is crucial for developing a safe real-world machine learning system. Current…

This work addresses the task of self-supervised learning (SSL) on a long-tailed dataset that aims to learn balanced and well-separated representations for downstream tasks such as image classification. This task is crucial because the real…

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…

A recent popular approach to out-of-distribution (OOD) detection is based on a self-supervised learning technique referred to as contrastive learning. There are two main variants of contrastive learning, namely instance and class…

To alleviate the cost of collecting and annotating large-scale point cloud datasets, we propose an unsupervised learning approach to learn features from unlabeled point cloud "3D object" dataset by using part contrasting and object…

Out-of-Distribution (OOD) detection is a crucial problem for the safe deployment of machine learning models identifying samples that fall outside of the training distribution, i.e. in-distribution data (ID). Most OOD works focus on the…

Handling out-of-distribution (OOD) samples has become a major stake in the real-world deployment of machine learning systems. This work explores the use of self-supervised contrastive learning to the simultaneous detection of two types of…

We present a new methodology for detecting out-of-distribution (OOD) images by utilizing norms of the score estimates at multiple noise scales. A score is defined to be the gradient of the log density with respect to the input data. Our…

It is essential for safety-critical applications of deep neural networks to determine when new inputs are significantly different from the training distribution. In this paper, we explore this out-of-distribution (OOD) detection problem for…

The ability to detect unfamiliar or unexpected images is essential for safe deployment of computer vision systems. In the context of classification, the task of detecting images outside of a model's training domain is known as…

In supervised machine learning, the assumption that training data is labelled correctly is not always satisfied. In this paper, we investigate an instance of labelling error for classification tasks in which the dataset is corrupted with…

One of the most promising approaches for unsupervised learning is combining deep representation learning and deep clustering. Some recent works propose to simultaneously learn representation using deep neural networks and perform clustering…

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…

Advancements in synthesized speech have created a growing threat of impersonation, making it crucial to develop deepfake algorithm recognition. One significant aspect is out-of-distribution (OOD) detection, which has gained notable…

Noisy images are a challenge to image compression algorithms due to the inherent difficulty of compressing noise. As noise cannot easily be discerned from image details, such as high-frequency signals, its presence leads to extra bits…

Semi-supervised learning methods have shown promising results in solving many practical problems when only a few labels are available. The existing methods assume that the class distributions of labeled and unlabeled data are equal;…

We present a principled approach for detecting out-of-distribution (OOD) and adversarial samples in deep neural networks. Our approach consists in modeling the outputs of the various layers (deep features) with parametric probability…

Methods which utilize the outputs or feature representations of predictive models have emerged as promising approaches for out-of-distribution (OOD) detection of image inputs. However, these methods struggle to detect OOD inputs that share…