Cartesian K-Means
A fundamental limitation of quantization techniques like the k-means clustering algorithm is the storage and runtime cost associated with the large numbers of clusters required to keep quantization errors small and model fidelity high. We develop new models with a compositional parameterization of cluster centers, so representational capacity increases super-linearly in the number of parameters. This allows one to effectively quantize data using billions or trillions of centers. We formulate two such models, Orthogonal k-means and Cartesian k-means. They are closely related to one another, to k-means, to methods for binary hash function optimization like ITQ [5], and to Product Quantization for vector quantization [7]. The models are tested on largescale ANN retrieval tasks (1M GIST, 1B SIFT features), and on codebook learning for object recognition (CIFAR-10).
Code (1)
Tasks
ClusteringObject RecognitionQuantizationRetrievalMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Optimized Cartesian $K$-Means
Product quantization-based approaches are effective to encode high-dimensional data points for approximate nearest neighbor search. The space is decomposed into a Cartesian product of low-dimensional subspaces, each of w…
QuantizationSparse Composite Quantization
The quantization techniques have shown competitive performance in approximate nearest neighbor search. The state-of-the-art algorithm, composite quantization, takes advantage of the compositionabity, i.e., the vector app…
QuantizationRetrievalNCDL: A Framework for Deep Learning on non-Cartesian Lattices
The use of non-Cartesian grids is a niche but important topic in sub-fields of the numerical sciences such as simulation and scientific visualization. However, non-Cartesian approaches are virtually unexplored in machine…
Deep LearningNCDL: A Framework for Deep Learning on non-Cartesian Lattices
The use of non-Cartesian grids is a niche but important topic in sub-fields of the numerical sciences such as simulation and scientific visualization. However, non-Cartesian approaches are virtually unexplored in machine…
Deep LearningA Cartesian-3j Framework for Machine Learning Interatomic Potentials
Machine learning interatomic potentials (MLIPs) have brought substantial gains in the extrapolation capability in computational chemistry. However, most equivariant models are typically built with spherical tensors (STs)…