Scalable Image Retrieval by Sparse Product Quantization
This work addresses a bottleneck in scalable image retrieval for applications like content-based search, though it is incremental as it builds on existing Product Quantization methods.
The paper tackles the problem of high quantization errors in Product Quantization for fast approximate nearest neighbor search in large-scale image retrieval by proposing Sparse Product Quantization (SPQ), which encodes feature vectors into sparse representations to minimize errors, achieving state-of-the-art results on four public image datasets.
Fast Approximate Nearest Neighbor (ANN) search technique for high-dimensional feature indexing and retrieval is the crux of large-scale image retrieval. A recent promising technique is Product Quantization, which attempts to index high-dimensional image features by decomposing the feature space into a Cartesian product of low dimensional subspaces and quantizing each of them separately. Despite the promising results reported, their quantization approach follows the typical hard assignment of traditional quantization methods, which may result in large quantization errors and thus inferior search performance. Unlike the existing approaches, in this paper, we propose a novel approach called Sparse Product Quantization (SPQ) to encoding the high-dimensional feature vectors into sparse representation. We optimize the sparse representations of the feature vectors by minimizing their quantization errors, making the resulting representation is essentially close to the original data in practice. Experiments show that the proposed SPQ technique is not only able to compress data, but also an effective encoding technique. We obtain state-of-the-art results for ANN search on four public image datasets and the promising results of content-based image retrieval further validate the efficacy of our proposed method.