Related papers: Inferring Spatial Uncertainty in Object Detection

Existing 3D object detectors encounter extreme challenges in localizing unseen 3D objects and recognizing them as unseen, which is a crucial technology in autonomous driving in the wild. To address these challenges, we propose practical…

The Jaccard index, also known as Intersection-over-Union (IoU), is one of the most critical evaluation metrics in image semantic segmentation. However, direct optimization of IoU score is very difficult because the learning objective is…

Autonomous driving systems face the formidable challenge of navigating intricate and dynamic environments with uncertainty. This study presents a unified prediction and planning framework that concurrently models short-term aleatoric…

Computer-aided diagnosis systems must make critical decisions from medical images that are often noisy, ambiguous, or conflicting, yet today's models are trained on overly simplistic labels that ignore diagnostic uncertainty. One-hot labels…

Despite rapid advances in AI, safety remains the main bottleneck to deploying machine-learning systems. A critical safety component is out-of-distribution detection: given an input, decide whether it comes from the same distribution as the…

The environments, in which autonomous cars act, are high-risky, dynamic, and full of uncertainty, demanding a continuous update of their sensory information and knowledge bases. The frequency of facing an unknown object is too high making…

Object detection and multiple object tracking (MOT) are essential components of self-driving systems. Accurate detection and uncertainty quantification are both critical for onboard modules, such as perception, prediction, and planning, to…

According to recent studies, commonly used computer vision datasets contain about 4% of label errors. For example, the COCO dataset is known for its high level of noise in data labels, which limits its use for training robust neural deep…

The proliferation of Deep Neural Networks has resulted in machine learning systems becoming increasingly more present in various real-world applications. Consequently, there is a growing demand for highly reliable models in many domains,…

Most existing trackers are based on using a classifier and multi-scale estimation to estimate the target state. Consequently, and as expected, trackers have become more stable while tracking accuracy has stagnated. While trackers adopt a…

Monocular 3D object detection plays a crucial role in autonomous driving. However, existing monocular 3D detection algorithms depend on 3D labels derived from LiDAR measurements, which are costly to acquire for new datasets and challenging…

Unbiased confidence estimates of neural networks are crucial especially for safety-critical applications. Many methods have been developed to calibrate biased confidence estimates. Though there is a variety of methods for classification,…

Recent efforts in deploying Deep Neural Networks for object detection in real world applications, such as autonomous driving, assume that all relevant object classes have been observed during training. Quantifying the performance of these…

Predictive uncertainty estimation is essential for deploying Deep Neural Networks in real-world autonomous systems. However, most successful approaches are computationally intensive. In this work, we attempt to address these challenges in…

Bounding box regression (BBR) is fundamental to object detection, where the regression loss is crucial for accurate localization. Existing IoU-based losses often incorporate handcrafted geometric penalties to address IoU's…

Robustly and accurately localizing objects in real-world environments can be challenging due to noisy data, hardware limitations, and the inherent randomness of physical systems. To account for these factors, existing works estimate the…

Modern oriented object detectors typically predict a set of bounding boxes and select the top-ranked ones based on estimated localization quality. Achieving high detection performance requires that the estimated quality closely aligns with…

In one-stage multi-object detection tasks, various intersection over union (IoU)-based solutions aim at smooth and stable convergence near the targets during training. However, IoU-based losses fail to correctly update the gradient of small…

Locating an object in a sequence of frames, given its appearance in the first frame of the sequence, is a hard problem that involves many stages. Usually, state-of-the-art methods focus on bringing novel ideas in the visual encoding or…

Jointly extracting entity pairs and their relations is challenging when working on distantly-supervised data with ambiguous or noisy labels. To mitigate such impact, we propose uncertainty-aware bootstrap learning, which is motivated by the…