Related papers: Strategies for Machine Learning Applied to Noisy H…

Deep learning methods have played a more and more important role in hyperspectral image classification. However, the general deep learning methods mainly take advantage of the information of sample itself or the pairwise information between…

Learning-based stereo matching has recently achieved promising results, yet still suffers difficulties in establishing reliable matches in weakly matchable regions that are textureless, non-Lambertian, or occluded. In this paper, we address…

The problem of noise in a general data acquisition procedure can be resolved more accurately if it is based on a model that describes well the distortions of the data including both spatial and intensity changes. The focus of this article…

In computer vision, the performance of deep neural networks (DNNs) is highly related to the feature extraction ability, i.e., the ability to recognize and focus on key pixel regions in an image. However, in this paper, we quantitatively and…

In this paper, we demonstrate a unique recipe to enhance the effectiveness of audio machine learning approaches by fusing pre-processing techniques into a deep learning model. Our solution accelerates training and inference performance by…

Training Deep neural networks (DNNs) on noisy labeled datasets is a challenging problem, because learning on mislabeled examples deteriorates the performance of the network. As the ground truth availability is limited with real-world noisy…

This paper proposes an effective modelling of sound event spectra with a hidden data-size-imbalance, for improved Acoustic Event Detection (AED). The proposed method models each event as an aggregated representation of a few latent factors,…

Deep neural networks (DNNs) can fit (or even over-fit) the training data very well. If a DNN model is trained using data with noisy labels and tested on data with clean labels, the model may perform poorly. This paper studies the problem of…

Deep learning methodology contributes a lot to the development of hyperspectral image (HSI) analysis community. However, it also makes HSI analysis systems vulnerable to adversarial attacks. To this end, we propose a masked spatial-spectral…

This study compares various superlearner and deep learning architectures (machine-learning-based and neural-network-based) for classification problems across several simulated and industrial datasets to assess performance and computational…

Deep convolutional neural network (DCNN for short) models are vulnerable to examples with small perturbations. Adversarial training (AT for short) is a widely used approach to enhance the robustness of DCNN models by data augmentation. In…

Magnetic particle imaging reconstructs tracer distributions using a system matrix obtained through time-consuming, noise-prone calibration measurements. Methods for addressing imperfections in measured system matrices increasingly rely on…

A growing need exists for efficient and accurate methods for detecting defects in semiconductor materials and devices. These defects can have a detrimental impact on the efficiency of the manufacturing process, because they cause critical…

We apply classical machine vision and machine deep learning methods to prototype signal classifiers for the search for extraterrestrial intelligence. Our novel approach uses two-dimensional spectrograms of measured and simulated radio…

The performances of Sound Event Detection (SED) systems are greatly limited by the difficulty in generating large strongly labeled dataset. In this work, we used two main approaches to overcome the lack of strongly labeled data. First, we…

Semi-supervised learning (SSL) can reduce the need for large labelled datasets by incorporating unlabelled data into the training. This is particularly interesting for semantic segmentation, where labelling data is very costly and…

The anatomical location of imaging features is of crucial importance for accurate diagnosis in many medical tasks. Convolutional neural networks (CNN) have had huge successes in computer vision, but they lack the natural ability to…

Deep Metric Learning (DML) is a group of techniques that aim to measure the similarity between objects through the neural network. Although the number of DML methods has rapidly increased in recent years, most previous studies cannot…

In the problem of learning mixtures of linear regressions, the goal is to learn a collection of signal vectors from a sequence of (possibly noisy) linear measurements, where each measurement is evaluated on an unknown signal drawn uniformly…

In the 21st-century information age, with the development of big data technology, effectively extracting valuable information from massive data has become a key issue. Traditional data mining methods are inadequate when faced with…