Learnable Histogram: Statistical Context Features for Deep Neural Networks
This work addresses the challenge of incorporating traditional statistical features into modern deep learning frameworks for computer vision applications, though it appears incremental in nature.
The authors tackled the problem of integrating statistical features like histograms into deep neural networks by proposing a learnable histogram layer that can be optimized end-to-end, showing it generalizes well to semantic segmentation and object detection tasks.
Statistical features, such as histogram, Bag-of-Words (BoW) and Fisher Vector, were commonly used with hand-crafted features in conventional classification methods, but attract less attention since the popularity of deep learning methods. In this paper, we propose a learnable histogram layer, which learns histogram features within deep neural networks in end-to-end training. Such a layer is able to back-propagate (BP) errors, learn optimal bin centers and bin widths, and be jointly optimized with other layers in deep networks during training. Two vision problems, semantic segmentation and object detection, are explored by integrating the learnable histogram layer into deep networks, which show that the proposed layer could be well generalized to different applications. In-depth investigations are conducted to provide insights on the newly introduced layer.