Related papers: Multiclass Confidence and Localization Calibration…

In safety-critical applications a probabilistic model is usually required to be calibrated, i.e., to capture the uncertainty of its predictions accurately. In multi-class classification, calibration of the most confident predictions only is…

The confidence calibration of deep learning-based perception models plays a crucial role in their reliability. Especially in the context of autonomous driving, downstream tasks like prediction and planning depend on accurate confidence…

Uncertainty calibration is crucial for various machine learning applications, yet it remains challenging. Many models exhibit hallucinations - confident yet inaccurate responses - due to miscalibrated confidence. Here, we show that the…

Uncertainty is a fundamental aspect of real-world scenarios, where perfect information is rarely available. Humans naturally develop complex internal models to navigate incomplete data and effectively respond to unforeseen or partially…

This paper describes an optimized single-stage deep convolutional neural network to detect objects in urban environments, using nothing more than point cloud data. This feature enables our method to work regardless the time of the day and…

Modern deep neural networks can produce badly calibrated predictions, especially when train and test distributions are mismatched. Training an ensemble of models and averaging their predictions can help alleviate these issues. We propose a…

Reliable confidence estimation for the predictions is important in many safety-critical applications. However, modern deep neural networks are often overconfident for their incorrect predictions. Recently, many calibration methods have been…

The many successes of deep neural networks (DNNs) over the past decade have largely been driven by computational scale rather than insights from biological intelligence. Here, we explore if these trends have also carried concomitant…

Deep neural networks have been shown to be highly miscalibrated. often they tend to be overconfident in their predictions. It poses a significant challenge for safety-critical systems to utilise deep neural networks (DNNs), reliably. Many…

Deep learning object detectors often return false positives with very high confidence. Although they optimize generic detection performance, such as mean average precision (mAP), they are not designed for reliability. For a reliable…

Fire is characterized by its sudden onset and destructive power, making early fire detection crucial for ensuring human safety and protecting property. With the advancement of deep learning, the application of computer vision in fire…

Providing ground truth supervision to train visual models has been a bottleneck over the years, exacerbated by domain shifts which degenerate the performance of such models. This was the case when visual tasks relied on handcrafted features…

Deep neural networks may perform poorly when training datasets are heavily class-imbalanced. Recently, two-stage methods decouple representation learning and classifier learning to improve performance. But there is still the vital issue of…

Cross domain object detection learns an object detector for an unlabeled target domain by transferring knowledge from an annotated source domain. Promising results have been achieved via Mean Teacher, however, pseudo labeling which is the…

In an increasing number of applications designers have access to multiple computer models which typically have different levels of fidelity and cost. Traditionally, designers calibrate these models one at a time against some high-fidelity…

Deep Neural Networks (DNN) are crucial in approximating nonlinear functions across diverse applications, ranging from image classification to control. Verifying specific input-output properties can be a highly challenging task due to the…

Temporal drift of sensory data is a severe problem impacting the data quality of wireless sensor networks (WSNs). With the proliferation of large-scale and long-term WSNs, it is becoming more important to calibrate sensors when the ground…

Deep neural object detection or segmentation networks are commonly trained with pristine, uncompressed data. However, in practical applications the input images are usually deteriorated by compression that is applied to efficiently transmit…

High degrees of disagreement among annotators can exist for ambiguous objects, e.g. in medical images, underscoring the challenges of establishing ground truth annotations in object detection tasks. Despite this, all existing object…

We present a novel detection method using a deep convolutional neural network (CNN), named AttentionNet. We cast an object detection problem as an iterative classification problem, which is the most suitable form of a CNN. AttentionNet…