Strong response consistency for more robust, disentangled and generalizable machine vision

强大的响应一致性，实现更稳健、更清晰和更通用的机器视觉

• 批准号: 448601360
• 负责人: Professor Dr. Wieland Brendel
• 金额: --
• 依托单位: Standort Tübingen
• 依托单位国家: 德国
• 项目类别: Independent Junior Research Groups
• 资助国家: 德国
• 项目状态: 未结题
• 来源: https://gepris.dfg.de/gepris/projekt/448601360?language=en
• 关键词: Strong; response; consistency; more; robust

Deep learning is the workhorse of today's machine intelligence that has produced numerous success stories all over science, industry, and society. However, this rapid and wide-spread success has masked four severe and fundamental issues that limit deep learning to comparatively few, narrowly defined application areas. For one, deep neural networks (DNNs) are not robust and even small input perturbations like JPEG compression or imperceptible but carefully engineered noise can derail their behavior. Second, the representations of DNNs are not disentangled and cannot be easily related to concepts understandable by humans. Third, the representations of DNNs do not generalize well to other tasks or domains without additional supervised training. Finally, we have little theoretical understanding of the representations learned by DNNs, making it difficult to solve the aforementioned issues.To make headway in these areas, I here propose a set of four consistency conditions that the visual representations of DNNs should fulfill. These conditions provide a strong theoretical grounding for unsupervised representation learning that opens up new avenues to study and enhance robustness, disentanglement, and generalization. By targeting these fundamental issues of deep learning, this work will reduce the gap between human and machine vision, increase reliability and explainability of DNNs, accelerate method development, and open up new application areas.

深度学习是当今机器智能的主力，它已经在科学、工业和社会中产生了无数成功的故事。然而，这种快速而广泛的成功掩盖了四个严重而根本的问题，这些问题将深度学习限制在相对较少的、狭义的应用领域。首先，深度神经网络(DNN)并不健壮，即使是JPEG压缩或难以察觉但精心设计的噪声等微小的输入扰动也会破坏它们的行为。其次，DNN的表示不是解开的，并且不容易与人类可以理解的概念相关联。第三，如果没有额外的监督训练，DNN的表示不能很好地推广到其他任务或领域。最后，我们对DNN学习到的表示在理论上了解很少，这使得解决上述问题变得困难。为了在这些领域取得进展，我在这里提出了DNN的视觉表示应该满足的四个一致性条件。这些条件为无监督表示学习提供了坚实的理论基础，为研究和增强健壮性、解缠性和泛化开辟了新的途径。通过针对深度学习的这些基本问题，本工作将缩小人类和机器视觉之间的差距，增加DNN的可靠性和可解释性，加快方法开发，并开辟新的应用领域。