Class selectivity is an attribute of a unit in deep neural networks, which characterizes the discriminative ability of units to a specific class. Intuitively, decisions made by several highly selective units are more interpretable since it is easier to be traced back to the origin while that made by complex combinations of lowly selective units are more difficult to interpret. In this work, we develop a novel way to directly train highly selective units, through which we are able to examine the performance of a network that only rely on highly selective units. Specifically, we train the network such that all the units in the penultimate layer only response to one specific class, which we named as class-specific unit. By innovatively formulating the problem using mutual information, we find that in such a case, the output of the model has a special form that all the probabilities over non-target classes are uniformly distributed. We then propose a minimax loss based on a game theoretic framework to achieve the goal. Nash equilibria are proved to exist and the outcome is consistent with our regularization objective. Experimental results show that the model trained with the proposed objective outperforms models trained with baseline objective among all the tasks we test. Our results shed light on the role of class-specific units by indicating that they can be directly used for decisions without relying on low selective units.

中文翻译：

---

迈向特定班级单位

类的选择性是深度神经网络中某个单元的属性，它表征了单元对特定类的区分能力。从直觉上讲，由几个高度选择性的单元做出的决定更易解释，因为它更容易追溯到原点，而由低选择性单元的复杂组合做出的决定则更难于解释。在这项工作中，我们开发了一种直接训练高度选择性单元的新颖方法，通过这种方法，我们可以检查仅依赖高度选择性单元的网络的性能。具体来说，我们训练网络，使倒数第二层中的所有单位仅响应一个特定的类别，我们将其称为特定于类别的单位。通过使用互信息创新性地解决问题，我们发现在这种情况下，模型的输出具有特殊形式，即非目标类别上的所有概率都均匀分布。然后，我们基于博弈论框架提出了极小极大损失以实现该目标。证明存在纳什均衡，且结果与我们的正则化目标一致。实验结果表明，在我们测试的所有任务中，以建议的目标训练的模型优于以基线目标训练的模型。我们的结果表明类别特定单位可以直接用于决策而无需依赖低选择性单位，从而阐明了它们的作用。证明存在纳什均衡，且结果与我们的正则化目标一致。实验结果表明，在我们测试的所有任务中，以建议的目标训练的模型优于以基线目标训练的模型。我们的结果表明类别特定单位可以直接用于决策而无需依赖低选择性单位，从而阐明了它们的作用。证明存在纳什均衡，且结果与我们的正则化目标一致。实验结果表明，在我们测试的所有任务中，以建议的目标训练的模型优于以基线目标训练的模型。我们的结果表明类别特定单位可以直接用于决策而无需依赖低选择性单位，从而阐明了它们的作用。