Related papers: Uncertainty-Aware Pedestrian Attribute Recognition…

Existing pedestrian attribute recognition methods are generally developed based on RGB frame cameras. However, these approaches are constrained by the limitations of RGB cameras, such as sensitivity to lighting conditions and motion blur,…

Fine-tuned large language models (LLMs) often exhibit overconfidence, particularly when trained on small datasets, resulting in poor calibration and inaccurate uncertainty estimates. Evidential Deep Learning (EDL), an uncertainty-aware…

Self-adaptive robots adjust their behaviors in response to unpredictable environmental changes. These robots often incorporate deep learning (DL) components into their software to support functionality such as perception, decision-making,…

Label Distribution Learning (LDL) aims to characterize the polysemy of an instance by building a set of descriptive degrees corresponding to the instance. In recent years, researchers seek to model to obtain an accurate label distribution…

Real-time crack segmentation is vital for structural health monitoring but is plagued by aleatoric uncertainties arising from varying lighting, blur, and texture ambiguity. Current uncertainty-aware approaches typically treat uncertainty…

Person re-identification (re-ID) and attribute recognition share a common target at learning pedestrian descriptions. Their difference consists in the granularity. Most existing re-ID methods only take identity labels of pedestrians into…

Learning against label noise is a vital topic to guarantee a reliable performance for deep neural networks. Recent research usually refers to dynamic noise modeling with model output probabilities and loss values, and then separates clean…

This work presents a novel data-driven multi-layered planning and control framework for the safe navigation of a class of unmanned ground vehicles (UGVs) in the presence of unknown stationary obstacles and additive modeling uncertainties.…

Anomaly detection in tabular data is challenging due to high dimensionality, complex feature dependencies, and heterogeneous noise. Many existing methods rely on proximity-based cues and may miss anomalies caused by violations of complex…

Deep reinforcement learning (DRL) has emerged as a promising approach for developing more intelligent autonomous vehicles (AVs). A typical DRL application on AVs is to train a neural network-based driving policy. However, the black-box…

Addressing the Out-of-Distribution (OoD) segmentation task is a prerequisite for perception systems operating in an open-world environment. Large foundational models are frequently used in downstream tasks, however, their potential for OoD…

We introduce the Evidential Transformer, an uncertainty-driven transformer model for improved and robust image retrieval. In this paper, we make several contributions to content-based image retrieval (CBIR). We incorporate probabilistic…

Anomaly detection in surveillance videos is challenging and important for ensuring public security. Different from pixel-based anomaly detection methods, pose-based methods utilize highly-structured skeleton data, which decreases the…

Most estimators collapse all uncertainty modes into a single confidence score, preventing reliable reasoning about when to allocate more compute or adjust inference. We introduce Uncertainty-Guided Inference-Time Selection, a lightweight…

T2 hyperintensities in spinal cord MR images are crucial biomarkers for conditions such as degenerative cervical myelopathy. However, current clinical diagnoses primarily rely on manual evaluation. Deep learning methods have shown promise…

A crucial requirement for machine learning algorithms is not only to perform well, but also to show robustness and adaptability when encountering novel scenarios. One way to achieve these characteristics is to endow the deep learning models…

Perception-based navigation systems are useful for unmanned ground vehicle (UGV) navigation in complex terrains, where traditional depth-based navigation schemes are insufficient. However, these data-driven methods are highly dependent on…

Given the temporal GPS coordinates from a large set of human agents, how can we model their mobility behavior toward effective anomaly (e.g. bad-actor or malicious behavior) detection without any labeled data? Human mobility and trajectory…

As instruction-tuned large language models (LLMs) evolve, aligning pretrained foundation models presents increasing challenges. Existing alignment strategies, which typically leverage diverse and high-quality data sources, often overlook…

Training deep convolutional neural networks usually requires a large amount of labeled data. However, it is expensive and time-consuming to annotate data for medical image segmentation tasks. In this paper, we present a novel…