arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2405.02564cs.CVcs.AIq-bio.NC
收藏

利用神经引导的深度神经网络探究人类视觉鲁棒性

Probing Human Visual Robustness with Neurally-Guided Deep Neural Networks

University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Cornell University(康奈尔大学);Stanford University(斯坦福大学)

Zhenan Shao, Linjian Ma, Yiqing Zhou, Yibo Jacky Zhang, Sanmi Koyejo, Bo Li, Diane M. Beck

AI总结:

本研究通过训练与人类腹侧视觉通路(VVS)不同层级神经响应对齐的DNN,验证了VVS表征空间的层级演化对视觉鲁棒性的作用,揭示了类别流形几何属性的关键影响,为开发更鲁棒的AI系统提供了思路。

摘要:

人类能够毫不费力地在动态视觉世界中活动,然而深度神经网络(DNNs)尽管在众多视觉任务上表现出色,却极易受到微小图像扰动的影响。过往理论认为,人类视觉鲁棒性源于沿大脑腹侧视觉通路(VVS)演化的表征空间,该空间对物体变换的容忍度逐渐提升。为验证鲁棒性是否由这种渐进过程支撑,而非仅局限于特化的高阶脑区,我们训练了DNNs,使其在执行视觉任务时,表征与来自VVS连续脑区的人类神经响应对齐。我们证明了DNN鲁棒性存在层级式提升:与更高阶VVS脑区对齐能带来更显著的提升。为探究这种鲁棒性提升背后的机制,我们检验了一个主流假说,该假说将人类鲁棒性归因于VVS中神经类别流形的独特几何结构。我们首先发现,更理想的流形属性,具体而言即更小的范围和更好的线性可分性,确实在人类VVS中逐步显现。这些属性可被神经对齐的DNNs继承,且能预测其后续的鲁棒性提升。此外,我们表明仅通过流形引导提供的神经流形监督,就足以定性复现层级式的鲁棒性提升。综上,这些结果凸显了VVS中不断演化的表征空间在实现鲁棒视觉推理中的关键作用,部分是通过形成线性可分性更强的类别流形实现的,这一发现或可用于开发更鲁棒的AI系统。

英文摘要:

Humans effortlessly navigate the dynamic visual world, yet deep neural networks (DNNs), despite excelling at many visual tasks, are surprisingly vulnerable to minor image perturbations. Past theories suggest that human visual robustness arises from a representational space that evolves along the ventral visual stream (VVS) of the brain to increasingly tolerate object transformations. To test whether robustness is supported by such progression as opposed to being confined exclusively to specialized higher-order regions, we trained DNNs to align their representations with human neural responses from consecutive VVS regions while performing visual tasks. We demonstrate a hierarchical improvement in DNN robustness: alignment to higher-order VVS regions leads to greater improvement. To investigate the mechanism behind such robustness gains, we test a prominent hypothesis that attributes human robustness to the unique geometry of neural category manifolds in the VVS. We first reveal that more desirable manifold properties, specifically, smaller extent and better linear separability, indeed emerge across the human VVS. These properties can be inherited by neurally aligned DNNs and predict their subsequent robustness gains. Furthermore, we show that supervision from neural manifolds alone, via manifold guidance, is sufficient to qualitatively reproduce the hierarchical robustness improvements. Together, these results highlight the critical role of the evolving representational space across VVS in achieving robust visual inference, in part through the formation of more linearly separable category manifolds, which may in turn be leveraged to develop more robust AI systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑