论文标题
链：深卷积神经网络的概念 - 荷尔语的分层推理解释
CHAIN: Concept-harmonized Hierarchical Inference Interpretation of Deep Convolutional Neural Networks
论文作者
论文摘要
随着网络的巨大成功，它见证了对内部网络机制解释的需求不断增长，尤其是对于净决策逻辑。为了应对挑战，提议提出概念性的分层推论（链）来解释净决策过程。对于被解释的净决定，该方法提出了链条解释，其中可以将净决策从高语义级别到低的语义级别层次推导为视觉概念。为了实现这一目标，我们顺序提出了三个模型，即概念协调模型，层次推理模型和概念 - 竖琴的分层推论模型。首先，在概念统一模型中，从高语义级别到低语义层的视觉概念与从深到浅层的网络单位保持一致。其次，在层次推理模型中，深层中的概念被分成浅层的单位。最后，在概念的荷尔语层次推理模型中，从其浅层概念中推断出一个深层的概念。经过几轮后，概念竖琴的分层推断从最高的语义水平向后进行，至最低的语义水平。最后，净决策被解释为一种概念性的 - 荷尔语层次结构推论，这与人类决策相当。同时，可以根据层次的视觉概念来解释特征学习的网层结构。在定量和定性实验中，我们证明了链在实例和班级水平上的有效性。
With the great success of networks, it witnesses the increasing demand for the interpretation of the internal network mechanism, especially for the net decision-making logic. To tackle the challenge, the Concept-harmonized HierArchical INference (CHAIN) is proposed to interpret the net decision-making process. For net-decisions being interpreted, the proposed method presents the CHAIN interpretation in which the net decision can be hierarchically deduced into visual concepts from high to low semantic levels. To achieve it, we propose three models sequentially, i.e., the concept harmonizing model, the hierarchical inference model, and the concept-harmonized hierarchical inference model. Firstly, in the concept harmonizing model, visual concepts from high to low semantic-levels are aligned with net-units from deep to shallow layers. Secondly, in the hierarchical inference model, the concept in a deep layer is disassembled into units in shallow layers. Finally, in the concept-harmonized hierarchical inference model, a deep-layer concept is inferred from its shallow-layer concepts. After several rounds, the concept-harmonized hierarchical inference is conducted backward from the highest semantic level to the lowest semantic level. Finally, net decision-making is explained as a form of concept-harmonized hierarchical inference, which is comparable to human decision-making. Meanwhile, the net layer structure for feature learning can be explained based on the hierarchical visual concepts. In quantitative and qualitative experiments, we demonstrate the effectiveness of CHAIN at the instance and class levels.
