The capability of Deep Neural Networks (DNNs) to recognize objects in orientations outside the distribution of the training data is not well understood. We present evidence that DNNs are capable of generalizing to objects in novel orientations by disseminating orientation-invariance obtained from familiar objects seen from many viewpoints. This capability strengthens when training the DNN with an increasing number of familiar objects, but only in orientations that involve 2D rotations of familiar orientations. We show that this dissemination is achieved via neurons tuned to common features between familiar and unfamiliar objects. These results implicate brain-like neural mechanisms for generalization.

翻译：深度神经网络（DNN）识别训练数据分布之外角度物体的能力尚不明确。我们提出证据表明，DNN能够通过传播从多视角观察的熟悉物体中获得的朝向不变性，从而泛化到新角度物体。当使用更多熟悉物体训练DNN时，这种能力会增强，但仅适用于涉及熟悉朝向二维旋转的角度。我们证明，这种传播是通过对熟悉与不熟悉物体共同特征敏感的神经元实现的。这些结果揭示了类似大脑的泛化神经机制。