将形态学击中或错过变换扩展到深度神经网络
Extending the Morphological Hit-or-Miss Transform to Deep Neural Networks
摘要:
虽然大多数深度学习架构都是建立在卷积基础上的,但人们正在探索形态学等替代基础,以实现可解释性及其与几何结构分析和处理的联系等目的。形态击中或错过操作的优点是,它考虑到前景和背景信息时,评估图像中的目标形状。在这里,我们确定了现有命中或失误神经定义的局限性,并制定了一个优化问题,以学习相对于更深层次架构的变换。为此,我们建模的语义重要的条件,命中和未命中的结构元素(SE)的交集应该是空的,我们提出了一种方法来表达不关心(DNC),这是重要的表示区域的SE是不相关的检测目标模式。我们的分析表明,卷积,事实上,通过其过滤器差异的语义解释,就像一个命中-未命中变换。在这些前提下,我们引入了一个扩展,在基准数据上优于传统的卷积。合成和基准数据上提供的定量实验表明,直接编码命中或失误变换提供了更好的可解释性与对象一致的学习形状,而我们的形态学启发的广义卷积产生更高的分类精度。最后,提供相对于单个形态层的定性命中和未命中过滤器可视化。
英文摘要:
While most deep learning architectures are built on convolution, alternative foundations like morphology are being explored for purposes like interpretability and its connection to the analysis and processing of geometric structures. The morphological hit-or-miss operation has the advantage that it takes into account both foreground and background information when evaluating target shape in an image. Herein, we identify limitations in existing hit-or-miss neural definitions and we formulate an optimization problem to learn the transform relative to deeper architectures. To this end, we model the semantically important condition that the intersection of the hit and miss structuring elements (SEs) should be empty and we present a way to express Don't Care (DNC), which is important for denoting regions of an SE that are not relevant to detecting a target pattern. Our analysis shows that convolution, in fact, acts like a hit-miss transform through semantic interpretation of its filter differences. On these premises, we introduce an extension that outperforms conventional convolution on benchmark data. Quantitative experiments are provided on synthetic and benchmark data, showing that the direct encoding hit-or-miss transform provides better interpretability on learned shapes consistent with objects whereas our morphologically inspired generalized convolution yields higher classification accuracy. Last, qualitative hit and miss filter visualizations are provided relative to single morphological layer.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。