Deep Spherical Quantization for Image Search
This addresses the need for efficient image retrieval in large-scale databases, but it is incremental as it builds upon existing hashing and quantization techniques.
The authors tackled the problem of generating compact binary codes for efficient large-scale image search by introducing Deep Spherical Quantization (DSQ), which learns a mapping to a low-dimensional discriminative space and quantizes features on a unit hypersphere, resulting in outperforming many state-of-the-art methods on three benchmarks.
Hashing methods, which encode high-dimensional images with compact discrete codes, have been widely applied to enhance large-scale image retrieval. In this paper, we put forward Deep Spherical Quantization (DSQ), a novel method to make deep convolutional neural networks generate supervised and compact binary codes for efficient image search. Our approach simultaneously learns a mapping that transforms the input images into a low-dimensional discriminative space, and quantizes the transformed data points using multi-codebook quantization. To eliminate the negative effect of norm variance on codebook learning, we force the network to L_2 normalize the extracted features and then quantize the resulting vectors using a new supervised quantization technique specifically designed for points lying on a unit hypersphere. Furthermore, we introduce an easy-to-implement extension of our quantization technique that enforces sparsity on the codebooks. Extensive experiments demonstrate that DSQ and its sparse variant can generate semantically separable compact binary codes outperforming many state-of-the-art image retrieval methods on three benchmarks.