Harmonizing the object recognition strategies of deep neural networks with humans
Harmonizing the object recognition strategies of deep neural networks with humans
复制标题
DOI：
10.48550/arxiv.2211.04533
复制
发表时间：
2022-11
期刊：
影响因子：
--
通讯作者：
Thomas Fel;Ivan Felipe;Drew Linsley;Thomas Serre
中科院分区：
文献类型：
--
作者：
Thomas Fel;Ivan Felipe;Drew Linsley;Thomas Serre
在过去十年中，深度神经网络（DNN）的许多成功在很大程度上是由计算规模驱动的，而不是来自生物智能的见解。在这里，我们探索这些趋势是否也伴随着解释人类依赖于物体识别的视觉策略的改进。我们通过比较人类和DNN中视觉策略的两个相关但不同的属性来做到这一点：他们认为重要的视觉特征在图像中的位置，以及他们如何使用这些特征来对对象进行分类。在ImageNet上训练的84个不同的DNN和三个独立的数据集中，测量了人类视觉策略在这些图像上识别对象的位置和方式，我们发现DNN分类准确性与人类视觉策略之间的系统权衡。随着其准确性的提高，最先进的DNN逐渐变得与人类不那么一致。我们用我们的神经协调器来纠正这个日益严重的问题：一个通用的训练例程，既可以调整DNN和人类视觉策略，又可以提高分类准确性。我们的工作首次证明了当今指导DNN设计的缩放定律[1-3]也产生了更差的人类视觉模型。我们在https://serre-lab.github.io/Harmonization上发布我们的代码和数据，以帮助该领域构建更多类似人类的DNN。
The many successes of deep neural networks (DNNs) over the past decade have largely been driven by computational scale rather than insights from biological intelligence. Here, we explore if these trends have also carried concomitant improvements in explaining the visual strategies humans rely on for object recognition. We do this by comparing two related but distinct properties of visual strategies in humans and DNNs: where they believe important visual features are in images and how they use those features to categorize objects. Across 84 different DNNs trained on ImageNet and three independent datasets measuring the where and the how of human visual strategies for object recognition on those images, we find a systematic trade-off between DNN categorization accuracy and alignment with human visual strategies for object recognition. State-of-the-art DNNs are progressively becoming less aligned with humans as their accuracy improves. We rectify this growing issue with our neural harmonizer: a general-purpose training routine that both aligns DNN and human visual strategies and improves categorization accuracy. Our work represents the first demonstration that the scaling laws [1-3] that are guiding the design of DNNs today have also produced worse models of human vision. We release our code and data at https://serre-lab.github.io/Harmonization to help the field build more human-like DNNs.