English
Related papers

Related papers: A Simple Unified Framework for Detecting Out-of-Di…

200 papers

It is crucial to detect when an instance lies downright too far from the training samples for the machine learning model to be trusted, a challenge known as out-of-distribution (OOD) detection. For neural networks, one approach to this task…

The increased success of Deep Learning (DL) has recently sparked large-scale deployment of DL models in many diverse industry segments. Yet, a crucial weakness of supervised model is the inherent difficulty in handling out-of-distribution…

Machine Learning · Computer Science 2021-07-15 Lixuan Yang , Dario Rossi

Deep neural networks often suffer from overconfidence which can be partly remedied by improved out-of-distribution detection. For this purpose, we propose a novel approach that allows for the generation of out-of-distribution datasets based…

Machine Learning · Computer Science 2021-05-10 Felix Möller , Diego Botache , Denis Huseljic , Florian Heidecker , Maarten Bieshaar , Bernhard Sick

Deep learning provides a powerful tool for machine perception when the observations resemble the training data. However, real-world robotic systems must react intelligently to their observations even in unexpected circumstances. This…

Machine Learning · Computer Science 2018-12-31 Rowan McAllister , Gregory Kahn , Jeff Clune , Sergey Levine

While deep learning models have seen widespread success in controlled environments, there are still barriers to their adoption in open-world settings. One critical task for safe deployment is the detection of anomalous or…

Machine Learning · Computer Science 2023-11-03 Connor Mclaughlin , Jason Matterer , Michael Yee

Out-of-distribution detection (OOD) deals with anomalous input to neural networks. In the past, specialized methods have been proposed to reject predictions on anomalous input. Similarly, it was shown that feature extraction models in…

Machine Learning · Computer Science 2022-01-25 Jan Diers , Christian Pigorsch

Deep neural networks (DNNs) are powerful nonlinear architectures that are known to be robust to random perturbations of the input. However, these models are vulnerable to adversarial perturbations--small input changes crafted explicitly to…

Machine Learning · Statistics 2017-11-17 Reuben Feinman , Ryan R. Curtin , Saurabh Shintre , Andrew B. Gardner

In this paper, we argue that the unsatisfactory out-of-distribution (OOD) detection performance of neural networks is mainly due to the SoftMax loss anisotropy and propensity to produce low entropy probability distributions in disagreement…

Machine Learning · Computer Science 2021-10-05 David Macêdo , Tsang Ing Ren , Cleber Zanchettin , Adriano L. I. Oliveira , Teresa Ludermir

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…

Computer Vision and Pattern Recognition · Computer Science 2024-04-03 Galadrielle Humblot-Renaux , Sergio Escalera , Thomas B. Moeslund

While state-of-the-art Deep Neural Network (DNN) models are considered to be robust to random perturbations, it was shown that these architectures are highly vulnerable to deliberately crafted perturbations, albeit being…

Machine Learning · Computer Science 2021-06-03 Omer Faruk Tuna , Ferhat Ozgur Catak , M. Taner Eskil

With the recently rapid development in deep learning, deep neural networks have been widely adopted in many real-life applications. However, deep neural networks are also known to have very little control over its uncertainty for unseen…

Machine Learning · Computer Science 2019-04-23 Wenhu Chen , Yilin Shen , Hongxia Jin , William Wang

There exist growing interests in intelligent systems for numerous medical imaging, image processing, and computer vision applications, such as face recognition, medical diagnosis, character recognition, and self-driving cars, among others.…

Computer Vision and Pattern Recognition · Computer Science 2023-02-06 Mohammad Shifat E Rabbi , Abu Hasnat Mohammad Rubaiyat , Yan Zhuang , Gustavo K Rohde

Modern applications of artificial neural networks have yielded remarkable performance gains in a wide range of tasks. However, recent studies have discovered that such modelling strategy is vulnerable to Adversarial Examples, i.e. examples…

Computer Vision and Pattern Recognition · Computer Science 2019-04-24 João Monteiro , Isabela Albuquerque , Zahid Akhtar , Tiago H. Falk

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…

Machine Learning · Computer Science 2024-04-17 Pietro Recalcati , Fabio Garcea , Luca Piano , Fabrizio Lamberti , Lia Morra

Despite high accuracy of Convolutional Neural Networks (CNNs), they are vulnerable to adversarial and out-distribution examples. There are many proposed methods that tend to detect or make CNNs robust against these fooling examples.…

Computer Vision and Pattern Recognition · Computer Science 2020-11-19 Arezoo Rajabi , Rakesh B. Bobba

Detecting out-of-distribution inputs for visual recognition models has become critical in safe deep learning. This paper proposes a novel hierarchical visual category modeling scheme to separate out-of-distribution data from in-distribution…

Computer Vision and Pattern Recognition · Computer Science 2024-08-29 Jinglun Li , Xinyu Zhou , Pinxue Guo , Yixuan Sun , Yiwen Huang , Weifeng Ge , Wenqiang Zhang

We propose a detector of adversarial samples that is based on the view of neural networks as discrete dynamic systems. The detector tells clean inputs from abnormal ones by comparing the discrete vector fields they follow through the…

Machine Learning · Computer Science 2023-06-09 Skander Karkar , Patrick Gallinari , Alain Rakotomamonjy

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…

Machine Learning · Computer Science 2023-02-24 Ido Galil , Mohammed Dabbah , Ran El-Yaniv

Training a classifier over a large number of classes, known as 'extreme classification', has become a topic of major interest with applications in technology, science, and e-commerce. Traditional softmax regression induces a gradient cost…

Machine Learning · Statistics 2020-02-18 Robert Bamler , Stephan Mandt

Machine learning models often encounter samples that are diverged from the training distribution. Failure to recognize an out-of-distribution (OOD) sample, and consequently assign that sample to an in-class label significantly compromises…

Computer Vision and Pattern Recognition · Computer Science 2022-12-06 Mohammadreza Salehi , Hossein Mirzaei , Dan Hendrycks , Yixuan Li , Mohammad Hossein Rohban , Mohammad Sabokrou