相关论文: Calibrated and Resource-Aware Super-Resolution for…

Vision-Language Models (VLMs) excel at many multimodal tasks, yet they frequently struggle with tasks requiring precise understanding and handling of fine-grained visual elements. This is mainly due to information loss during image encoding…

Real-world image super-resolution (SR) is a challenging image translation problem. Low-resolution (LR) images are often generated by various unknown transformations rather than by applying simple bilinear down-sampling on high-resolution…

The rapid development of 3D object detection systems for self-driving cars has significantly improved accuracy. However, these systems struggle to generalize across diverse driving environments, which can lead to safety-critical failures in…

Safety validation for Level 4 autonomous vehicles (AVs) is currently bottlenecked by the inability to scale the detection of rare, high-risk long-tail scenarios using traditional rule-based heuristics. We present Deep-Flow, an unsupervised…

Riverine floods pose a considerable risk to many communities. Improving flood hazard projections has the potential to inform the design and implementation of flood risk management strategies. Current flood hazard projections are uncertain,…

In the domain of moment retrieval, accurately identifying temporal segments within videos based on natural language queries remains challenging. Traditional methods often employ pre-trained models that struggle with fine-grained information…

Radio-based localization in dynamic environments, such as urban and vehicular settings, requires systems that efficiently adapt to varying signal conditions and environmental changes. Factors like multipath interference and obstructions…

Millimeter-wave (mmWave) radars are indispensable for perception tasks of autonomous vehicles, thanks to their resilience in challenging weather conditions. Yet, their deployment is often limited by insufficient spatial resolution for…

Safe learning is central to AI-enabled robots where a single failure may lead to catastrophic results. Barrier-based method is one of the dominant approaches for safe robot learning. However, this method is not scalable, hard to train, and…

Accurate and reliable probability predictions are essential for multi-class supervised learning tasks, where well-calibrated models enable rational decision-making. While isotonic regression has proven effective for binary calibration, its…

Inspired by human visual attention, we propose a novel inverse reinforcement learning formulation using Maximum Entropy Deep Inverse Reinforcement Learning (MEDIRL) for predicting the visual attention of drivers in accident-prone…

As the orbital environment around Earth becomes increasingly crowded with debris, active debris removal (ADR) missions face significant challenges in ensuring safe operations while minimizing the risk of in-orbit collisions. This study…

Autonomous and semi-autonomous systems are using deep learning models to improve decision-making. However, deep classifiers can be overly confident in their incorrect predictions, a major issue especially in safety-critical domains. The…

Transformer-based scientific foundation models are increasingly deployed in high-stakes settings, but current architectures give deterministic outputs and provide limited support for calibrated predictive uncertainty. We propose Stochastic…

Although deep learning has significantly improved Face Recognition (FR), dramatic performance deterioration may occur when processing Low Resolution (LR) faces. To alleviate this, approaches based on unified feature space are proposed with…

Text-to-image diffusion models have achieved remarkable progress in recent years. However, training models for high-resolution image generation remains challenging, particularly when training data and computational resources are limited. In…

The interest in using reinforcement learning (RL) controllers in safety-critical applications such as robot navigation around pedestrians motivates the development of additional safety mechanisms. Running RL-enabled systems among uncertain…

Many real-world phenomena are observed at multiple resolutions. Predictive models designed to predict these phenomena typically consider different resolutions separately. This approach might be limiting in applications where predictions are…

Log messages record important system runtime information and are useful for detecting anomalous behaviors and managing modern software systems. Many supervised and unsupervised learning methods have been proposed recently for log-based…

Image restoration algorithms such as super resolution (SR) are indispensable pre-processing modules for object detection in low quality images. Most of these algorithms assume the degradation is fixed and known a priori. However, in…