Related papers: Learning from Convolution-based Unlearnable Datase…

The volume of "free" data on the internet has been key to the current success of deep learning. However, it also raises privacy concerns about the unauthorized exploitation of personal data for training commercial models. It is thus crucial…

State-of-the-art, high capacity deep neural networks not only require large amounts of labelled training data, they are also highly susceptible to label errors in this data, typically resulting in large efforts and costs and therefore…

Concept Bottleneck Models (CBMs) enhance interpretability by explaining predictions through human-understandable concepts but typically assume that training and test data share the same distribution. This assumption often fails under domain…

In unsupervised domain adaptation (UDA), classifiers for the target domain are trained with massive true-label data from the source domain and unlabeled data from the target domain. However, it may be difficult to collect fully-true-label…

This paper describes a neural network layer, named Ursa, that uses a constellation of points to learn classification information from point cloud data. Unlike other machine learning classification problems where the task is to classify an…

With the development of artificial intelligence technology, Federated Learning (FL) model has been widely used in many industries for its high efficiency and confidentiality. Some researchers have explored its confidentiality and designed…

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…

Recent work has shown that deep neural networks are highly sensitive to tiny perturbations of input images, giving rise to adversarial examples. Though this property is usually considered a weakness of learned models, we explore whether it…

The widespread availability of publicly accessible medical images has significantly propelled advancements in various research and clinical fields. Nonetheless, concerns regarding unauthorized training of AI systems for commercial purposes…

Concealed object detection (COD) in cluttered scenes is significant for various image processing applications. However, due to that concealed objects are always similar to their background, it is extremely hard to distinguish them. Here,…

Background: When using deep learning models, there are many possible vulnerabilities and some of the most worrying are the adversarial inputs, which can cause wrong decisions with minor perturbations. Therefore, it becomes necessary to…

Deep learning systems extensively use convolution operations to process input data. Though convolution is clearly defined for structured data such as 2D images or 3D volumes, this is not true for other data types such as sparse point…

Efficiently managing and utilizing large-scale medical imaging datasets with limited resources presents significant challenges. While coreset selection helps reduce computational costs, its effectiveness in medical data remains limited due…

Deep learning architectures are showing great promise in various computer vision domains including image classification, object detection, event detection and action recognition. In this study, we investigate various aspects of…

Recent advances in deep learning rely heavily on massive datasets, leading to substantial storage and training costs. Dataset pruning aims to alleviate this demand by discarding redundant examples. However, many existing methods require…

An important goal in visual recognition is to devise image representations that are invariant to particular transformations. In this paper, we address this goal with a new type of convolutional neural network (CNN) whose invariance is…

Ensembles of Convolutional neural networks have shown remarkable results in learning discriminative semantic features for image classification tasks. Though, the models in the ensemble often concentrate on similar regions in images. This…

When deep learning is applied to visual object recognition, data augmentation is often used to generate additional training data without extra labeling cost. It helps to reduce overfitting and increase the performance of the algorithm. In…

The diagnosis of thyroid nodule cancers commonly utilizes ultrasound images. Several studies showed that deep learning algorithms designed to classify benign and malignant thyroid nodules could match radiologists' performance. However, data…

Deep neural networks often rely on spurious correlations in training data, leading to biased or unfair predictions in safety-critical domains such as medicine and autonomous driving. While conventional bias mitigation typically requires…