CVMar 27, 2018

Compassionately Conservative Balanced Cuts for Image Segmentation

arXiv:1803.09903v12 citations
Originality Incremental advance
AI Analysis

This work addresses a specific limitation in graph-based image segmentation for computer vision applications, representing an incremental improvement over existing methods.

The authors tackled the problem of Normalized Cut's strong bias against singleton partitions in image segmentation by proposing the Compassionately Conservative Balanced (CCB) Cut family, which improves accuracy and region size variability on the BSDS500 database compared to NCut-based methods.

The Normalized Cut (NCut) objective function, widely used in data clustering and image segmentation, quantifies the cost of graph partitioning in a way that biases clusters or segments that are balanced towards having lower values than unbalanced partitionings. However, this bias is so strong that it avoids any singleton partitions, even when vertices are very weakly connected to the rest of the graph. Motivated by the Bühler-Hein family of balanced cut costs, we propose the family of Compassionately Conservative Balanced (CCB) Cut costs, which are indexed by a parameter that can be used to strike a compromise between the desire to avoid too many singleton partitions and the notion that all partitions should be balanced. We show that CCB-Cut minimization can be relaxed into an orthogonally constrained $\ell_τ$-minimization problem that coincides with the problem of computing Piecewise Flat Embeddings (PFE) for one particular index value, and we present an algorithm for solving the relaxed problem by iteratively minimizing a sequence of reweighted Rayleigh quotients (IRRQ). Using images from the BSDS500 database, we show that image segmentation based on CCB-Cut minimization provides better accuracy with respect to ground truth and greater variability in region size than NCut-based image segmentation.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes