相关论文: Class-Level Logit Perturbation

Neural networks are known to be vulnerable to adversarial examples, inputs that have been intentionally perturbed to remain visually similar to the source input, but cause a misclassification. It was recently shown that given a dataset and…

Deep neural networks are powerful and popular learning models that achieve state-of-the-art pattern recognition performance on many computer vision, speech, and language processing tasks. However, these networks have also been shown…

An important characteristic of neural networks is their ability to learn representations of the input data with effective features for prediction, which is believed to be a key factor to their superior empirical performance. To better…

With the great success of deep neural networks, adversarial learning has received widespread attention in various studies, ranging from multi-class learning to multi-label learning. However, existing adversarial attacks toward multi-label…

Because deep learning is vulnerable to noisy labels, sample selection techniques, which train networks with only clean labeled data, have attracted a great attention. However, if the labels are dominantly corrupted by few classes, these…

Item mining, a fundamental task for collecting statistical data from users, has raised increasing privacy concerns. To address these concerns, local differential privacy (LDP) was proposed as a privacy-preserving technique. Existing LDP…

List-wise learning to rank methods are considered to be the state-of-the-art. One of the major problems with these methods is that the ambiguous nature of relevance labels in learning to rank data is ignored. Ambiguity of relevance labels…

Deep neural networks are highly vulnerable to adversarial examples, i.e.,small perturbations that can significantly degrade model performance. While adversarial training has become the primary defense strategy, most studies focus on…

Noisy Labels are commonly present in data sets automatically collected from the internet, mislabeled by non-specialist annotators, or even specialists in a challenging task, such as in the medical field. Although deep learning models have…

Perturbation with diverse unlabeled data has proven beneficial for semi-supervised medical image segmentation (SSMIS). While many works have successfully used various perturbation techniques, a deeper understanding of learning perturbations…

Improving the classification of multi-class imbalanced data is more difficult than its two-class counterpart. In this paper, we use deep neural networks to train new representations of tabular multi-class data. Unlike the typically…

Label smoothing (LS) is a popular regularisation method for training neural networks as it is effective in improving test accuracy and is simple to implement. ``Hard'' one-hot labels are ``smoothed'' by uniformly distributing probability…

In many applications of classifier learning, training data suffers from label noise. Deep networks are learned using huge training data where the problem of noisy labels is particularly relevant. The current techniques proposed for learning…

In this paper, we propose a novel approach for learning multi-label classifiers with the help of privileged information. Specifically, we use similarity constraints to capture the relationship between available information and privileged…

Current face recognition tasks are usually carried out on high-quality face images, but in reality, most face images are captured under unconstrained or poor conditions, e.g., by video surveillance. Existing methods are featured by learning…

This paper addresses a multi-label predictive fault classification problem for multidimensional time-series data. While fault (event) detection problems have been thoroughly studied in literature, most of the state-of-the-art techniques…

Discriminative linear models are a popular tool in machine learning. These can be generally divided into two types: The first is linear classifiers, such as support vector machines, which are well studied and provide state-of-the-art…

A recently-proposed technique called self-adaptive training augments modern neural networks by allowing them to adjust training labels on the fly, to avoid overfitting to samples that may be mislabeled or otherwise non-representative. By…

A key challenge for machine intelligence is to learn new visual concepts without forgetting the previously acquired knowledge. Continual learning is aimed towards addressing this challenge. However, there is a gap between existing…

Learning in the presence of label noise is a challenging yet important task: it is crucial to design models that are robust in the presence of mislabeled datasets. In this paper, we discover that a new class of loss functions called the…