Deep Unsupervised Hashing by Global and Local Consistency

Hashing is widely-used in approximate nearest neighbor search for its computational efficiency. Most of the existing unsupervised hashing methods are based on local consistency that the Hamming distance between two images should be small if their features are similar. However, many false similar pairs may be included for the insufficient representation of features. Here we proposed deep unsupervised hashing by Global and Local Consistency (GLC). Specifically, GLC has two components named semantic information generating and semantic consistency learning, and each component is conducted from both global and local views. From local view, GLC introduces reliable graph and penalty graph to capture local signals with high confidence to preserve the semantic structure. From global view, GLC includes a distribution loss to capture the global consistency with cluster signals. Extensive experimental results on three widely-used benchmark datasets show that GLC performs better than existing state- of-the-art methods.