mlsanityData to 14 Oct 2026

RAT: Boosting Misclassification Detection Ability without Extra Data

arXiv 2503.14783 ↗First posted 18 Mar 2025cs.CV cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

As deep neural networks(DNN) become increasingly prevalent, particularly in high-stakes areas such as autonomous driving and healthcare, the ability to detect incorrect predictions of models and intervene accordingly becomes crucial for safety. In this work, we investigate the detection of misclassified inputs for image classification models from the lens of adversarial perturbation: we propose to use robust radius (a.k.a. input-space margin) as a confidence metric and design two efficient estimation algorithms, RR-BS and RR-Fast, for misclassification detection. Furthermore, we design a training method called Radius Aware Training (RAT) to boost models' ability to identify mistakes. Extensive experiments show our method could achieve up to 29.3% reduction on AURC and 21.62% reduction in FPR@95TPR, compared with previous methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 35 references that are in the map. First posted on arXiv 18 Mar 2025.

Builds on

26 of 35 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2016Densely Connected Convolutional Networkscited by 6,720
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  6. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  7. 2013Intriguing properties of neural networkscited by 5,155
  8. 2016Wide Residual Networkscited by 3,070
  9. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  10. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  11. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  12. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
14 more
  1. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  2. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  3. 2017Selective Classification for Deep Neural Networkscited by 852
  4. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
  5. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
  6. 2019Adversarial Training for Free!cited by 643
  7. 2019A Survey of Autonomous Driving: Common Practices and Emerging Technologiescited by 379
  8. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 334
  9. 2017Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Artcited by 182
  10. 2020Exactly Computing the Local Lipschitz Constant of ReLU Networkscited by 102
  11. 2021DOCTOR: A Simple Method for Detecting Misclassification Errorscited by 53
  12. 2023OpenMix: Exploring Outlier Samples for Misclassification Detectioncited by 38
  13. 2021Exploring Misclassifications of Robust Neural Networks to Enhance Adversarial Attackscited by 33
  14. 2023A Data-Driven Measure of Relative Uncertainty for Misclassification Detectioncited by 14

Built on by

Not cited yet.