paper-with-me

Papers

DOCTOR: A Simple Method for Detecting Misclassification Errors

2021-06-04 · NeurIPS 2021 12 · Federica Granese, Marco Romanelli, Daniele Gorla, Catuscia Palamidessi, Pablo Piantanida

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.

📄 PDF Abstract BibTeX arXiv:2106.02395

Code (1)

doctor-public-submission/DOCTOR 공식 구현

Tasks

Object RecognitionSentiment Analysis

Similar Papers 제목 키워드 기반

Detecting Adversarial Examples and Other Misclassifications in Neural Networks by Introspection

2019-05-22 · Jonathan Aigrain, Marcin Detyniecki

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

2020-10-05 · Xin Qiu, Risto Miikkulainen

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 Processes

OpenMix: Exploring Outlier Samples for Misclassification Detection

2023-03-30 · CVPR 2023 1 · Fei Zhu, Zhen Cheng, Xu-Yao Zhang, Cheng-Lin Liu

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 Knowledge

Model Doctor for Diagnosing and Treating Segmentation Error

2023-02-17 · Zhijie Jia, Lin Chen, Kaiwen Hu, Lechao Cheng 외

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 Segmentation

Debugging Machine Learning Tasks

2016-03-23 · Aleksandar Chakarov, Aditya Nori, Sriram Rajamani, Shayak Sen 외

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