Iterative Quantization: A Procrustean Approach to Learning Binary Codes

This paper addresses the problem of learning similaritypreserving binary codes for efficient retrieval in large-scale image collections. We propose a simple and efficient alternating minimization scheme for finding a rotation of zerocentered data so as to minimize the quantization error of mapping this data to the vertices of a zero-centered binary hypercube. This method, dubbed iterative quantization (ITQ), has connections to multi-class spectral clustering and to the orthogonal Procrustes problem, and it can be used both with unsupervised data embeddings such as PCA and supervised embeddings such as canonical correlation analysis (CCA). Our experiments show that the resulting binary coding schemes decisively outperform several other state-of-the-art methods.

• Type: Journal
• Year: 2011
• Where: CVPR
• Authors: Yunchao Gong, Svetlana Lazebnik
• Keywords: Computer Vision, CVPR 2011, Efficient Alternating Minimization, Unsupervised Data Embeddings, Zero-centered Binary Hypercube