mlsanityData to 14 Oct 2026

Having Second Thoughts? Let's hear it

arXiv 2311.15356 ↗First posted 26 Nov 2023cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep learning models loosely mimic bottom-up signal pathways from low-order sensory areas to high-order cognitive areas. After training, DL models can outperform humans on some domain-specific tasks, but their decision-making process has been known to be easily disrupted. Since the human brain consists of multiple functional areas highly connected to one another and relies on intricate interplays between bottom-up and top-down (from high-order to low-order areas) processing, we hypothesize that incorporating top-down signal processing may make DL models more robust. To address this hypothesis, we propose a certification process mimicking selective attention and test if it could make DL models more robust. Our empirical evaluations suggest that this newly proposed certification can improve DL models' accuracy and help us build safety measures to alleviate their vulnerabilities with both artificial and natural adversarial examples.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 39 references that are in the map. First posted on arXiv 26 Nov 2023.

Builds on

26 of 39 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  5. 2016Densely Connected Convolutional Networkscited by 6,720
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  7. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  8. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  9. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  10. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  11. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  12. 2019Natural Adversarial Examplescited by 1,408
14 more
  1. 2016Understanding intermediate layers using linear classifier probescited by 1,353
  2. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
  3. 2016The Mythos of Model Interpretabilitycited by 721
  4. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  5. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 351
  6. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 334
  7. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 279
  8. 2018Adversarial Attacks and Defences: A Surveycited by 259
  9. 2016Improving the Robustness of Deep Neural Networks via Stability Trainingcited by 156
  10. 2019advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorchcited by 69
  11. 2021A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?cited by 48
  12. 2018Stop Explaining Black Box Machine Learning Models for High Stakes Decisions and Use Interpretable Models Insteadcited by 40
  13. 2019A Review of Deep Learning with Special Emphasis on Architectures, Applications and Recent Trendscited by 26
  14. 2022Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)cited by 18

Built on by

Not cited yet.