Differentiable Histogram with Hard-Binning
This work provides a more accurate differentiable histogram for researchers and practitioners who need to incorporate histogram-like features into deep learning models.
This paper proposes a differentiable histogram that directly approximates the hard-binning operation of conventional histograms. It achieves an absolute approximation error of 0.000158 when compared to a histogram computed using Numpy.
The simplicity and expressiveness of a histogram render it a useful feature in different contexts including deep learning. Although the process of computing a histogram is non-differentiable, researchers have proposed differentiable approximations, which have some limitations. A differentiable histogram that directly approximates the hard-binning operation in conventional histograms is proposed. It combines the strength of existing differentiable histograms and overcomes their individual challenges. In comparison to a histogram computed using Numpy, the proposed histogram has an absolute approximation error of 0.000158.