Supervised deep hashing for scalable face image retrieval

作者：

Highlights：

• We propose a novel Deep Hashing based on Classification and Quantization errors for face image retrieval.

• It jointly learns feature representations of images, hashing functions and classifiers.

• The quantization errors and the prediction errors jointly guide the learning of the deep network.

• The DeepFeature layer is fully connected to both the third and fourth layers to capture multi-scale features.

• Experiments on three benchmarks demonstrate the superior performance of our work.

摘要

•We propose a novel Deep Hashing based on Classification and Quantization errors for face image retrieval.•It jointly learns feature representations of images, hashing functions and classifiers.•The quantization errors and the prediction errors jointly guide the learning of the deep network.•The DeepFeature layer is fully connected to both the third and fourth layers to capture multi-scale features.•Experiments on three benchmarks demonstrate the superior performance of our work.

论文关键词：Image retrieval,Supervised hashing,Binary codes,Deep learning

论文评审过程：Received 14 September 2016, Revised 19 March 2017, Accepted 24 March 2017, Available online 29 March 2017, Version of Record 21 November 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.03.028