Deep Spherical Quantization for Image Search
| Autor: | Sepehr Eghbali, Ladan Tahvildari |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Normalization (statistics) Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) Deep learning Quantization (signal processing) Computer Science - Computer Vision and Pattern Recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Codebook Pattern recognition 02 engineering and technology 010501 environmental sciences Hypersphere 01 natural sciences Convolutional neural network Discriminative model 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Binary code Artificial intelligence business Quantization (image processing) Image retrieval 0105 earth and related environmental sciences |
| Zdroj: | CVPR |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|