Climbing on Pyramids
Jean Serra, Bangalore Ravi Kiran

TL;DR
This paper introduces a novel energy minimization method for identifying optimal cuts in hierarchical partitions, ensuring the energy increases with hierarchy level, applicable to various energy types.
Contribution
It proposes a new hierarchical energy minimization approach that guarantees scale-increasing properties for finding optimal cuts in hierarchies.
Findings
Effective in identifying optimal hierarchy cuts
Applicable to a broad class of energies including separable and supremum-composed energies
Ensures energy climbing property in hierarchical segmentation
Abstract
A new approach is proposed for finding the "best cut" in a hierarchy of partitions by energy minimization. Said energy must be "climbing" i.e. it must be hierarchically and scale increasing. It encompasses separable energies and those composed under supremum.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsComputability, Logic, AI Algorithms · Digital Image Processing Techniques · semigroups and automata theory
