DOCTOR: A Simple Method for Detecting Misclassification Errors
Deep neural networks (DNNs) have shown to perform very well on large scale object recognition problems and lead to widespread use for real-world applications, including situations where DNN are implemented as "black boxes". A promising approach to secure their use is to accept decisions that are likely to be correct while discarding the others. In this work, we propose DOCTOR, a simple method that aims to identify whether the prediction of a DNN classifier should (or should not) be trusted so that, consequently, it would be possible to accept it or to reject it. Two scenarios are investigated: Totally Black Box (TBB) where only the soft-predictions are available and Partially Black Box (PBB) where gradient-propagation to perform input pre-processing is allowed. Empirically, we show that DOCTOR outperforms all state-of-the-art methods on various well-known images and sentiment analysis datasets. In particular, we observe a reduction of up to $4\%$ of the false rejection rate (FRR) in the PBB scenario. DOCTOR can be applied to any pre-trained model, it does not require prior information about the underlying dataset and is as simple as the simplest available methods in the literature.
Code (1)
Tasks
Object RecognitionSentiment AnalysisSimilar Papers 제목 키워드 기반
Detecting Adversarial Examples and Other Misclassifications in Neural Networks by Introspection
Despite having excellent performances for a wide variety of tasks, modern neural networks are unable to provide a reliable confidence value allowing to detect misclassifications. This limitation is at the heart of what i…
Detecting Misclassification Errors in Neural Networks with a Gaussian Process Model
As neural network classifiers are deployed in real-world applications, it is crucial that their failures can be detected reliably. One practical solution is to assign confidence scores to each prediction, then use these …
Gaussian ProcessesOpenMix: Exploring Outlier Samples for Misclassification Detection
Reliable confidence estimation for deep neural classifiers is a challenging yet fundamental requirement in high-stakes applications. Unfortunately, modern deep neural networks are often overconfident for their erroneous …
World KnowledgeModel Doctor for Diagnosing and Treating Segmentation Error
Despite the remarkable progress in semantic segmentation tasks with the advancement of deep neural networks, existing U-shaped hierarchical typical segmentation networks still suffer from local misclassification of categ…
modelSegmentationSemantic SegmentationDebugging Machine Learning Tasks
Unlike traditional programs (such as operating systems or word processors) which have large amounts of code, machine learning tasks use programs with relatively small amounts of code (written in machine learning librarie…
BIG-bench Machine Learning