paper-with-me

홈 › Papers

Cartesian K-Means

2013-06-01 · CVPR 2013 6 · Mohammad Norouzi, David J. Fleet

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).

📄 PDF Abstract BibTeX

Code (1)

norouzi/ckmeans 공식 구현

Tasks

ClusteringObject RecognitionQuantizationRetrieval

Methods 이 논문이 사용한 방법론

k-Means Clustering k-Means Clustering is a clustering algorithm that divides a training set into $k$ different clusters of examples that are near each other. It works by initializing $k$…

Similar Papers 제목 키워드 기반

Optimized Cartesian $K$-Means

2014-05-16 · Jianfeng Wang, Jingdong Wang, Jingkuan Song, Xin-Shun Xu 외

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…

Quantization

Sparse Composite Quantization

2015-06-01 · CVPR 2015 6 · Ting Zhang, Guo-Jun Qi, Jinhui Tang, Jingdong Wang

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…

QuantizationRetrieval

NCDL: A Framework for Deep Learning on non-Cartesian Lattices

2023-09-21

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 Learning

NCDL: A Framework for Deep Learning on non-Cartesian Lattices

2023-09-21 · NeurIPS 2023 11

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 Learning

A Cartesian-3j Framework for Machine Learning Interatomic Potentials

2025-12-18 · Zemin Xu, Chenyu Wu, Wenbo Xie, P. Hu arxiv

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)…