Out-of-Distribution Example Detection in Deep Neural Networks using Distance to Modelled Embedding

• URL: http://arxiv.org/abs/2108.10673v1
• Date: Tue, 24 Aug 2021 12:28:04 GMT
• Title: Out-of-Distribution Example Detection in Deep Neural Networks using Distance to Modelled Embedding
• Authors: Rickard Sj\"ogren and Johan Trygg
• Abstract summary: We present Distance to Modelled Embedding (DIME) that we use to detect out-of-distribution examples during prediction time. By approximating the training set embedding into feature space as a linear hyperplane, we derive a simple, unsupervised, highly performant and computationally efficient method.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Adoption of deep learning in safety-critical systems raise the need for understanding what deep neural networks do not understand after models have been deployed. The behaviour of deep neural networks is undefined for so called out-of-distribution examples. That is, examples from another distribution than the training set. Several methodologies to detect out-of-distribution examples during prediction-time have been proposed, but these methodologies constrain either neural network architecture, how the neural network is trained, suffer from performance overhead, or assume that the nature of out-of-distribution examples are known a priori. We present Distance to Modelled Embedding (DIME) that we use to detect out-of-distribution examples during prediction time. By approximating the training set embedding into feature space as a linear hyperplane, we derive a simple, unsupervised, highly performant and computationally efficient method. DIME allows us to add prediction-time detection of out-of-distribution examples to neural network models without altering architecture or training while imposing minimal constraints on when it is applicable. In our experiments, we demonstrate that by using DIME as an add-on after training, we efficiently detect out-of-distribution examples during prediction and match state-of-the-art methods while being more versatile and introducing negligible computational overhead.

Related papers

• Deep Neural Networks Tend To Extrapolate Predictably [51.303814412294514]
  neural network predictions tend to be unpredictable and overconfident when faced with out-of-distribution (OOD) inputs. We observe that neural network predictions often tend towards a constant value as input data becomes increasingly OOD. We show how one can leverage our insights in practice to enable risk-sensitive decision-making in the presence of OOD inputs.
  arXiv  Detail & Related papers  (2023-10-02T03:25:32Z)
• Window-Based Distribution Shift Detection for Deep Neural Networks [21.73028341299301]
  We study the case of monitoring the healthy operation of a deep neural network (DNN) receiving a stream of data. Using selective prediction principles, we propose a distribution deviation detection method for DNNs. Our novel detection method performs on-par or better than the state-of-the-art, while consuming substantially lower time.
  arXiv  Detail & Related papers  (2022-10-19T21:27:25Z)
• A Novel Explainable Out-of-Distribution Detection Approach for Spiking Neural Networks [6.100274095771616]
  This work presents a novel OoD detector that can identify whether test examples input to a Spiking Neural Network belong to the distribution of the data over which it was trained. We characterize the internal activations of the hidden layers of the network in the form of spike count patterns. A local explanation method is devised to produce attribution maps revealing which parts of the input instance push most towards the detection of an example as an OoD sample.
  arXiv  Detail & Related papers  (2022-09-30T11:16:35Z)
• Learning to Learn with Generative Models of Neural Network Checkpoints [71.06722933442956]
  We construct a dataset of neural network checkpoints and train a generative model on the parameters. We find that our approach successfully generates parameters for a wide range of loss prompts. We apply our method to different neural network architectures and tasks in supervised and reinforcement learning.
  arXiv  Detail & Related papers  (2022-09-26T17:59:58Z)
• Scalable computation of prediction intervals for neural networks via matrix sketching [79.44177623781043]
  Existing algorithms for uncertainty estimation require modifying the model architecture and training procedure. This work proposes a new algorithm that can be applied to a given trained neural network and produces approximate prediction intervals.
  arXiv  Detail & Related papers  (2022-05-06T13:18:31Z)
• Model2Detector:Widening the Information Bottleneck for Out-of-Distribution Detection using a Handful of Gradient Steps [12.263417500077383]
  Out-of-distribution detection is an important capability that has long eluded vanilla neural networks. Recent advances in inference-time out-of-distribution detection help mitigate some of these problems. We show how our method consistently outperforms the state-of-the-art in detection accuracy on popular image datasets.
  arXiv  Detail & Related papers  (2022-02-22T23:03:40Z)
• Adversarial Examples Detection with Bayesian Neural Network [57.185482121807716]
  We propose a new framework to detect adversarial examples motivated by the observations that random components can improve the smoothness of predictors. We propose a novel Bayesian adversarial example detector, short for BATer, to improve the performance of adversarial example detection.
  arXiv  Detail & Related papers  (2021-05-18T15:51:24Z)
• Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning [50.24174211654775]
  We present a novel contrastive self-supervised learning framework for anomaly detection on attributed networks. Our framework fully exploits the local information from network data by sampling a novel type of contrastive instance pair. A graph neural network-based contrastive learning model is proposed to learn informative embedding from high-dimensional attributes and local structure.
  arXiv  Detail & Related papers  (2021-02-27T03:17:20Z)
• A Bayesian Perspective on Training Speed and Model Selection [51.15664724311443]
  We show that a measure of a model's training speed can be used to estimate its marginal likelihood. We verify our results in model selection tasks for linear models and for the infinite-width limit of deep neural networks. Our results suggest a promising new direction towards explaining why neural networks trained with gradient descent are biased towards functions that generalize well.
  arXiv  Detail & Related papers  (2020-10-27T17:56:14Z)
• Uncertainty-Aware Deep Classifiers using Generative Models [7.486679152591502]
  Deep neural networks are often ignorant about what they do not know and overconfident when they make uninformed predictions. Some recent approaches quantify uncertainty directly by training the model to output high uncertainty for the data samples close to class boundaries or from the outside of the training distribution. We develop a novel neural network model that is able to express both aleatoric and epistemic uncertainty to distinguish decision boundary and out-of-distribution regions.
  arXiv  Detail & Related papers  (2020-06-07T15:38:35Z)
• Detecting Adversarial Examples in Learning-Enabled Cyber-Physical Systems using Variational Autoencoder for Regression [4.788163807490198]
  It has been shown that deep neural networks (DNN) are not robust and adversarial examples can cause the model to make a false prediction. The paper considers the problem of efficiently detecting adversarial examples in LECs used for regression in CPS. We demonstrate the method using an advanced emergency braking system implemented in an open source simulator for self-driving cars.
  arXiv  Detail & Related papers  (2020-03-21T11:15:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.