Deep Neural Networks as a Computational Model for Human Shape Sensitivity.
Deep Neural Networks as a Computational Model for Human Shape Sensitivity.
复制标题
DOI：
10.1371/journal.pcbi.1004896
复制
发表时间：
2016-04
影响因子：
4.3
通讯作者：
Op de Beeck HP
中科院分区：
文献类型：
--
作者：
Kubilius J;Bracci S;Op de Beeck HP
物体识别理论一致认为形状是最重要的，但是对于形状如何被表示却没有达成共识，到目前为止，试图实现一个可以与现实刺激一起工作的形状感知模型的尝试基本上失败了。最近的研究表明，最先进的卷积“深度”神经网络（dnn）捕获了人类物体感知的重要方面。我们假设这些成功可能部分与人类对物体形状的表征有关。在这里，我们证明了对人类和灵长类动物视觉特征的形状特征的敏感性，在训练dnn从自然照片中识别通用物体时出现。我们表明，这些模型解释了人类对几个基准行为和神经刺激集的形状判断，而早期的模型大多失败了。特别是，尽管从未针对此类刺激进行过明确的训练，但dnn对形状的微小变化和非偶然特性具有敏锐的敏感性，这些特性长期以来一直被认为是物体识别的基础。更引人注目的是，当在形状和类别成员分离的具有挑战性的刺激集上进行测试时，最复杂的模型架构捕捉到了人类形状敏感性以及从人类判断中出现的类别结构的某些方面。总的来说，这些结果表明卷积神经网络不仅学习了物体类别的物理正确表征，而且还开发了感知上准确的形状表征空间。通过为多个任务训练深度架构，一个更完整的人类对象表示模型可能就在眼前，这是人类发展的特征。形状在物体识别中起着重要的作用。尽管经过多年的研究，没有一种视觉模型可以像人类对自然图像的视觉那样解释形状的理解。鉴于最近深度神经网络（dnn）在物体识别方面的成功，我们假设dnn实际上可能学会捕捉感知上显著的形状维度。使用各种刺激集，我们在这里证明了几个dnn的输出层发展了与人类感知形状判断密切相关的表征。令人惊讶的是，即使这些模型从未受过明确的形状处理训练，它们对形状的敏感性也会在这些模型中发展起来。此外，我们表明这些模型也代表了人类语义判断的范畴对象相似性，尽管程度较低。综上所述，我们的研究结果提出了一个令人兴奋的想法，即dnn不仅捕获刺激的客观维度，如它们的类别，而且还捕获它们的主观或感知方面，如人类判断的形状和语义相似性。
Theories of object recognition agree that shape is of primordial importance, but there is no consensus about how shape might be represented, and so far attempts to implement a model of shape perception that would work with realistic stimuli have largely failed. Recent studies suggest that state-of-the-art convolutional ‘deep’ neural networks (DNNs) capture important aspects of human object perception. We hypothesized that these successes might be partially related to a human-like representation of object shape. Here we demonstrate that sensitivity for shape features, characteristic to human and primate vision, emerges in DNNs when trained for generic object recognition from natural photographs. We show that these models explain human shape judgments for several benchmark behavioral and neural stimulus sets on which earlier models mostly failed. In particular, although never explicitly trained for such stimuli, DNNs develop acute sensitivity to minute variations in shape and to non-accidental properties that have long been implicated to form the basis for object recognition. Even more strikingly, when tested with a challenging stimulus set in which shape and category membership are dissociated, the most complex model architectures capture human shape sensitivity as well as some aspects of the category structure that emerges from human judgments. As a whole, these results indicate that convolutional neural networks not only learn physically correct representations of object categories but also develop perceptually accurate representational spaces of shapes. An even more complete model of human object representations might be in sight by training deep architectures for multiple tasks, which is so characteristic in human development. Shape plays an important role in object recognition. Despite years of research, no models of vision could account for shape understanding as found in human vision of natural images. Given recent successes of deep neural networks (DNNs) in object recognition, we hypothesized that DNNs might in fact learn to capture perceptually salient shape dimensions. Using a variety of stimulus sets, we demonstrate here that the output layers of several DNNs develop representations that relate closely to human perceptual shape judgments. Surprisingly, such sensitivity to shape develops in these models even though they were never explicitly trained for shape processing. Moreover, we show that these models also represent categorical object similarity that follows human semantic judgments, albeit to a lesser extent. Taken together, our results bring forward the exciting idea that DNNs capture not only objective dimensions of stimuli, such as their category, but also their subjective, or perceptual, aspects, such as shape and semantic similarity as judged by humans.