相关论文: Data augmentation and pre-trained networks for ext…

Deep neural networks are increasingly being used to detect and diagnose medical conditions using medical imaging. Despite their utility, these models are highly vulnerable to adversarial attacks and distribution shifts, which can affect…

Most recent gains in visual recognition have originated from the inclusion of attention mechanisms in deep convolutional networks (DCNs). Because these networks are optimized for object recognition, they learn where to attend using only a…

Visual inspection software has become a key factor in the manufacturing industry for quality control and process monitoring. Semantic segmentation models have gained importance since they allow for more precise examination. These models,…

Deep neural networks for image quality enhancement typically need large quantities of highly-curated training data comprising pairs of low-quality images and their corresponding high-quality images. While high-quality image acquisition is…

Discovering distinct features and their relations from data can help us uncover valuable knowledge crucial for various tasks, e.g., classification. In neuroimaging, these features could help to understand, classify, and possibly prevent…

Leveraging deep learning models for Anomaly Detection (AD) has seen widespread use in recent years due to superior performances over traditional methods. Recent deep methods for anomalies in images learn better features of normality in an…

Deep Convolutional Neural Networks have made an incredible progress in many Computer Vision tasks. This progress, however, often relies on the availability of large amounts of the training data, required to prevent over-fitting, which in…

Detecting anomalies in musculoskeletal radiographs is of paramount importance for large-scale screening in the radiology workflow. Supervised deep networks take for granted a large number of annotations by radiologists, which is often…

Deep neural networks (DNN) which are employed in perception systems for autonomous driving require a huge amount of data to train on, as they must reliably achieve high performance in all kinds of situations. However, these DNN are usually…

Visual surveillance aims to stably detect a foreground object using a continuous image acquired from a fixed camera. Recent deep learning methods based on supervised learning show superior performance compared to classical background…

This paper investigates the application of deep convolutional neural networks with prohibitively small datasets to the problem of macular edema segmentation. In particular, we investigate several different heavily regularized architectures.…

Deep supervision, which involves extra supervisions to the intermediate features of a neural network, was widely used in image classification in the early deep learning era since it significantly reduces the training difficulty and eases…

Recently, great progress has been made in 3D deep learning with the emergence of deep neural networks specifically designed for 3D point clouds. These networks are often trained from scratch or from pre-trained models learned purely from…

Semi-supervised learning algorithms reduce the high cost of acquiring labeled training data by using both labeled and unlabeled data during learning. Deep Convolutional Networks (DCNs) have achieved great success in supervised tasks and as…

Automated surface inspection is an important task in many manufacturing industries and often requires machine learning driven solutions. Supervised approaches, however, can be challenging, since it is often difficult to obtain large amounts…

Surface anomaly detection plays an important quality control role in many manufacturing industries to reduce scrap production. Machine-based visual inspections have been utilized in recent years to conduct this task instead of human…

Self-supervised learning methods for computer vision have demonstrated the effectiveness of pre-training feature representations, resulting in well-generalizing Deep Neural Networks, even if the annotated data are limited. However,…

Large-scale labeled data are generally required to train deep neural networks in order to obtain better performance in visual feature learning from images or videos for computer vision applications. To avoid extensive cost of collecting and…

Deep learning models in medical imaging often encounter challenges when adapting to new clinical settings unseen during training. Test-time adaptation offers a promising approach to optimize models for these unseen domains, yet its…

Deep neural networks have achieved state-of-the-art results in various vision and/or language tasks. Despite the use of large training datasets, most models are trained by iterating over single input-output pairs, discarding the remaining…