Generalized residual vector quantization for large scale data
This work addresses the need for efficient vector quantization in large-scale similarity search, classification, and object retrieval, representing an incremental improvement over existing methods.
The authors tackled the problem of vector quantization for large-scale data by proposing a generalized residual vector quantization (GRVQ) framework that iteratively minimizes quantization error, which substantially outperforms existing methods in quantization accuracy and computational efficiency on several benchmark datasets.
Vector quantization is an essential tool for tasks involving large scale data, for example, large scale similarity search, which is crucial for content-based information retrieval and analysis. In this paper, we propose a novel vector quantization framework that iteratively minimizes quantization error. First, we provide a detailed review on a relevant vector quantization method named \textit{residual vector quantization} (RVQ). Next, we propose \textit{generalized residual vector quantization} (GRVQ) to further improve over RVQ. Many vector quantization methods can be viewed as the special cases of our proposed framework. We evaluate GRVQ on several large scale benchmark datasets for large scale search, classification and object retrieval. We compared GRVQ with existing methods in detail. Extensive experiments demonstrate our GRVQ framework substantially outperforms existing methods in term of quantization accuracy and computation efficiency.