Convolutional Neural Networks (CNNs) are commonly thought to recognise objects by learning increasingly complex representations of object shapes. Some recent studies hint to a more important role of image textures. We here put these conflicting hypotheses to a quantitative test by evaluating CNNs and human observers on images with a texture-shape cue conflict. We show that ImageNet-trained CNNs are strongly biased towards recognising textures rather than shapes, which is in stark contrast to human behavioural evidence and reveals fundamentally different classification strategies. We then demonstrate that the same standard architecture (ResNet-50) that learns a texture-based representation on ImageNet is able to learn a shape-based representation instead when trained on "Stylized-ImageNet", a stylized version of ImageNet. This provides a much better fit for human behavioural performance in our well-controlled psychophysical lab setting (nine experiments totalling 48,560 psychophysical trials across 97 observers) and comes with a number of unexpected emergent benefits such as improved object detection performance and previously unseen robustness towards a wide range of image distortions, highlighting advantages of a shape-based representation.

这篇文章通过对卷积神经网络（CNNs）和人类观察者在具有纹理-形状线索冲突的图像上进行实验，揭示了CNN在识别物体时更倾向于识别纹理而非形状的基本不同分类策略，同时表明将CNN在Stylized-ImageNet数据集上训练可以学习到形状为基础的表示，可以更好地拟合人类行为表现，同时具有提高物体检测性能和对各种图像扭曲的鲁棒性的优点。

ImageNet训练的CNN偏向于纹理; 增加形状偏差可以提高准确性和鲁棒性