Ask a Question

Prefer a chat interface with context about you and your work?

Unsupervised Learning of Edges

Unsupervised Learning of Edges

Data-driven approaches for edge detection have proven effective and achieve top results on modern benchmarks. However, all current data-driven edge detectors require manual supervision for training in the form of hand-labeled region segments or object boundaries. Specifically, human annotators mark semantically meaningful edges which are subsequently used for training. Is …