相关论文: Scaling Out-of-Distribution Detection for Real-Wor…

Out-of-distribution detection seeks to identify novelties, samples that deviate from the norm. The task has been found to be quite challenging, particularly in the case where the normal data distribution consists of multiple semantic…

When deployed for risk-sensitive tasks, deep neural networks must be able to detect instances with labels from outside the distribution for which they were trained. In this paper we present a novel framework to benchmark the ability of…

Out-of-distribution (OOD) detection is a task that detects OOD samples during inference to ensure the safety of deployed models. However, conventional benchmarks have reached performance saturation, making it difficult to compare recent OOD…

Deep neural networks are increasingly used in a wide range of technologies and services, but remain highly susceptible to out-of-distribution (OOD) samples, that is, drawn from a different distribution than the original training set. A…

The detection of out of distribution samples for image classification has been widely researched. Safety critical applications, such as autonomous driving, would benefit from the ability to localise the unusual objects causing the image to…

The ability to detect unfamiliar or unexpected images is essential for safe deployment of computer vision systems. In the context of classification, the task of detecting images outside of a model's training domain is known as…

We present a new methodology for detecting out-of-distribution (OOD) images by utilizing norms of the score estimates at multiple noise scales. A score is defined to be the gradient of the log density with respect to the input data. Our…

This paper presents a novel evaluation framework for Out-of-Distribution (OOD) detection that aims to assess the performance of machine learning models in more realistic settings. We observed that the real-world requirements for testing OOD…

Most classification and segmentation datasets assume a closed-world scenario in which predictions are expressed as distribution over a predetermined set of visual classes. However, such assumption implies unavoidable and often unnoticeable…

Understanding the surrounding environment is fundamental in autonomous driving and robotic perception. Distinguishing between known classes and previously unseen objects is crucial in real-world environments, as done in Anomaly…

Unsupervised continual learning aims to learn new tasks incrementally without requiring human annotations. However, most existing methods, especially those targeted on image classification, only work in a simplified scenario by assuming all…

Deep Neural Networks are powerful models that attained remarkable results on a variety of tasks. These models are shown to be extremely efficient when training and test data are drawn from the same distribution. However, it is not clear how…

In the real world, a learning system could receive an input that is unlike anything it has seen during training. Unfortunately, out-of-distribution samples can lead to unpredictable behaviour. We need to know whether any given input belongs…

Supervised classification methods often assume the train and test data distributions are the same and that all classes in the test set are present in the training set. However, deployed classifiers often require the ability to recognize…

Medical image diagnosis can be achieved by deep neural networks, provided there is enough varied training data for each disease class. However, a hitherto unknown disease class not encountered during training will inevitably be…

Deep learning models for image classification are typically trained under the "closed-world" assumption with a predefined set of image classes. However, when the models are deployed they may be faced with input images not belonging to the…

Detecting test-time distribution shift has emerged as a key capability for safely deployed machine learning models, with the question being tackled under various guises in recent years. In this paper, we aim to provide a consolidated view…

The usage of deep neural networks in safety-critical systems is limited by our ability to guarantee their correct behavior. Runtime monitors are components aiming to identify unsafe predictions and discard them before they can lead to…

Out-of-distribution (OOD) detection is an important topic for real-world machine learning systems, but settings with limited in-distribution samples have been underexplored. Such few-shot OOD settings are challenging, as models have scarce…

Applying machine learning to increasingly high-dimensional problems with sparse or biased training data increases the risk that a model is used on inputs outside its training domain. For such out-of-distribution (OOD) inputs, the model can…