Skip to main content

Robust Machine Learning Algorithms and Systems for Detection and Mitigation of Adversarial Attacks and Anomalies Proceedings of a Workshop (2019) / Chapter Skim
Currently Skimming:

8 Recent Trends in Machine Learning, Part 3
Pages 39-45

The Chapter Skim interface presents what we've algorithmically identified as the most significant single chunk of text within every page in the chapter.
Select key terms on the right to highlight them within pages of the chapter.


From page 39...
... In the ImageNet classification challenge, Hoffman's team found that performance started to approach near perfect on the test set; this improvement came as a result of leveraging millions of training examples effectively and expanding capacities of models over time. While people expect similarly strong performance in real-world applications, such stellar performance is unlikely.
Read the entire page →
From page 40...
... Rama Chellappa, University of Maryland, College Park, asked how this is related to maximum mean discrepancy for domain adaptation, and Hoffman responded that this approach uses a different statistical alignment technique, different learning bounds, and a different algorithm but that the maximum mean discrepancy technique is also relatively easy to implement in practice. By first training a classifier to differentiate between the source and the target, it is possible to create a minimization function; if it is possible to observe a difference, the collections are far apart in the feature space.
Read the entire page →
From page 41...
... This gives a learning algorithm that does not require labels in the deployment setting but does make it possible to update the underlying representation so as to learn a domain-invariant feature space. She added that it is also possible to think about domain adversarial learning directly by aligning in pixel space, similar to the work of generative adversarial networks (GANs)
Read the entire page →
From page 42...
... Using the mean intersection over the union of the data, it is possible to improve raw pixel accuracy using unsupervised alignment techniques. The algorithm looks at the pixel level and the feature level and examines how to best make changes to the representation so as to still perform original classification tasks but also to learn biases in invariance space.
Read the entire page →
From page 43...
... The third project Rohrbach presented was about causal factors for visuomotor policies. The objective of this project was to predict vehicle motion and communicate to the human in natural language why a certain driving behavior occurred (i.e., generating textual explanation of how visual evidence is compatible with a decision)
Read the entire page →
From page 44...
... A workshop participant asked Rohrbach if her team has tried applying the justification to naturally occurring or intentionally generated adversarial images. Rohrbach said that although they have not tried that yet, they have done something related for VQA.
Read the entire page →
From page 45...
... Qualitative results reveal that one cannot rely on single attention, because if something is no longer present, the system has a difficult time understanding that change and associating the same object in two scenes. So, the approach she described has two attention mechanisms to discover the change and highlight in an explainable manner where the right evidence is located.
Read the entire page →

Key Terms

  • machine learning
  • training data
  • deep learning
  • feature space
  • participant asked

  • google street
  • workshop participant
  • street view
  • adaptation example
  • statistical alignment

  • common sense
  • judy hoffman
  • deployment setting
  • textual justification
  • alignment techniques

  • georgia institute
  • source data
  • domain adversarial
  • target data
  • learning directly

  • learning approaches
  • adversarial learning
  • space alignment
  • visual environments
  • audience participant

  • standard gan
  • improve performance
  • driving behavior
  • aligned attention
  • strong performance


    • This material may be derived from roughly machine-read images, and so is provided only to facilitate research.
    More information on Chapter Skim is available.