Related papers: Dual-level Fuzzy Learning with Patch Guidance for …

Reconstruction networks are prevalently used in unsupervised anomaly and Out-of-Distribution (OOD) detection due to their independence from labeled anomaly data. However, in multi-class datasets, the effectiveness of anomaly detection is…

To achieve parsimonious inference in per-pixel labeling tasks with a limited computational budget, we propose a \emph{Pixel-wise Attentional Gating} unit (\emph{PAG}) that learns to selectively process a subset of spatial locations at each…

Deep learning is advancing EEG processing for automated epileptic seizure detection and onset zone localization, yet its performance relies heavily on high-quality annotated training data. However, scalp EEG is susceptible to high noise…

The challenges of high intra-class variance yet low inter-class fluctuations in fine-grained visual categorization are more severe with few labeled samples, \textit{i.e.,} Fine-Grained categorization problems under the Few-Shot setting…

Deep Learning systems (DL) based on Deep Neural Networks (DNNs) are more and more used in various aspects of our life, including unmanned vehicles, speech processing, and robotics. However, due to the limited dataset and the dependence on…

This paper introduces a two-stage framework designed to enhance long-tail class incremental learning, enabling the model to progressively learn new classes, while mitigating catastrophic forgetting in the context of long-tailed data…

High-quality labeled datasets are essential for deep learning. Traditional manual annotation methods are not only costly and inefficient but also pose challenges in specialized domains where expert knowledge is needed. Self-supervised…

Learning with Noisy Labels (LNL) aims to improve the model generalization when facing data with noisy labels, and existing methods generally assume that noisy labels come from known classes, called closed-set noise. However, in real-world…

Deep learning (DL) systems are increasingly applied to safety-critical domains such as autonomous driving cars. It is of significant importance to ensure the reliability and robustness of DL systems. Existing testing methodologies always…

The success of Deep Neural Network (DNN) models significantly depends on the quality of provided annotations. In medical image segmentation, for example, having multiple expert annotations for each data point is common to minimize…

Document image dewarping remains a challenging task in the deep learning era. While existing methods have improved by leveraging text line awareness, they typically focus only on a single horizontal dimension. In this paper, we propose a…

Recognizing multiple labels of images is a fundamental but challenging task in computer vision, and remarkable progress has been attained by localizing semantic-aware image regions and predicting their labels with deep convolutional neural…

Automatic and accurate segmentation for retinal and choroidal layers of Optical Coherence Tomography (OCT) is crucial for detection of various ocular diseases. However, because of the variations in different equipments, OCT data obtained…

We propose a multi-level method to increase the accuracy of machine learning algorithms for approximating observables in scientific computing, particularly those that arise in systems modeled by differential equations. The algorithm relies…

Fine-grained domain generalization (FGDG) is a more challenging task than traditional DG tasks due to its small inter-class variations and relatively large intra-class disparities. When domain distribution changes, the vulnerability of…

The presence of label noise often misleads the training of deep neural networks. Departing from the recent literature which largely assumes the label noise rate is only determined by the true label class, the errors in human-annotated…

Road detection or traversability analysis has been a key technique for a mobile robot to traverse complex off-road scenes. The problem has been mainly formulated in early works as a binary classification one, e.g. associating pixels with…

Fine-Grained Domain Generalization (FGDG) presents greater challenges than conventional domain generalization due to the subtle inter-class differences and relatively pronounced intra-class variations inherent in fine-grained recognition…

Annotation variability remains a substantial challenge in medical image segmentation, stemming from ambiguous imaging boundaries and diverse clinical expertise. Traditional deep learning methods producing single deterministic segmentation…

Deep neural networks achieve high accuracy on image classification tasks. Yet, they often produce overconfident predictions as which fail to express epistemic uncertainty, and frequently violate logical or structural constraints present in…