Shearlets as Feature Extractor for Semantic Edge Detection: The Model-Based and Data-Driven Realm

TL;DR

This paper introduces a hybrid approach combining shearlets and neural networks to improve semantic edge detection, effectively addressing the distracted supervision paradox and enhancing performance in applications like biomedical imaging.

Contribution

It presents a novel hybrid method that integrates model-based shearlets with data-driven neural networks for superior semantic edge detection.

Findings

Significantly outperforms previous methods in semantic edge detection

Effective in applications like tomographic reconstruction

Addresses the distracted supervision paradox successfully

Abstract

Semantic edge detection has recently gained a lot of attention as an image processing task, mainly due to its wide range of real-world applications. This is based on the fact that edges in images contain most of the semantic information. Semantic edge detection involves two tasks, namely pure edge detecion and edge classification. Those are in fact fundamentally distinct in terms of the level of abstraction that each task requires, which is known as the distracted supervision paradox that limits the possible performance of a supervised model in semantic edge detection. In this work, we will present a novel hybrid method to avoid the distracted supervision paradox and achieve high-performance in semantic edge detection. Our approach is based on a combination of the model-based concept of shearlets, which provides probably optimally sparse approximations of a model-class of images, and the data-driven method of a suitably designed convolutional neural netwok. Finally, we present several applications such as tomographic reconstruction and show that our approach signifiantly outperforms former methods, thereby indicating the value of such hybrid methods for the area in biomedical imaging.