mlsanityData to 14 Oct 2026

Two out of Three (ToT): using self-consistency to make robust predictions

arXiv 2505.12642 ↗First posted 19 May 2025cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep learning (DL) can automatically construct intelligent agents, deep neural networks (alternatively, DL models), that can outperform humans in certain tasks. However, the operating principles of DL remain poorly understood, making its decisions incomprehensible. As a result, it poses a great risk to deploy DL in high-stakes domains in which mistakes or errors may lead to critical consequences. Here, we aim to develop an algorithm that can help DL models make more robust decisions by allowing them to abstain from answering when they are uncertain. Our algorithm, named `Two out of Three (ToT)', is inspired by the sensitivity of the human brain to conflicting information. ToT creates two alternative predictions in addition to the original model prediction and uses the alternative predictions to decide whether it should provide an answer or not.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 41 references that are in the map. First posted on arXiv 19 May 2025.

Builds on

19 of 41 references.

References · 19

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  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. 2013Intriguing properties of neural networkscited by 5,155
  7. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  8. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 767
  9. 2016The Mythos of Model Interpretabilitycited by 721
  10. 2019Adversarial Training for Free!cited by 643
  11. 2021How to train your ViT? Data, Augmentation, and Regularization in Vision Transformerscited by 569
  12. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 351
7 more
  1. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 279
  2. 2018Adversarial Attacks and Defences: A Surveycited by 259
  3. 2019advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorchcited by 69
  4. 2021A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?cited by 48
  5. 2019A Review of Deep Learning with Special Emphasis on Architectures, Applications and Recent Trendscited by 26
  6. 2023Training on Foveated Images Improves Robustness to Adversarial Attackscited by 5
  7. 2020ALCN: Adaptive Local Contrast Normalizationcited by 2

Built on by

Not cited yet.