Learning Efficient Binary Codes from High-level Feature representations for Multi-Label Image Retrieval

Abstract-Due to the efficiency and effectiveness of hashing technologies, they have become increasingly popular in large scale image semantic retrieval. However, existing hash methods suppose that the data distributions satisfy the manifold assumption that semantic similar samples tend to lie on a low- dimensional manifold, which will be weakened due to the large intra-class variation. Moreover, these methods learn hash functions by relaxing the discrete constraints on binary codes to real value, which will introduce large quantization loss. To tackle the above problems, proposes a novel unsupervised hashing algorithm to learn efficient binary codes from high-level feature representations.which will map images with similar (visually or semantically) high-level feature representations to similar binary codes. To solve the corresponding optimization problem involving nonnegative and discrete variables, we develop an efficient optimization algorithm to reduce quantization loss with guaranteed convergence in theory. Extensive experiments show that our proposed method outperforms the state-of-the-art hashing methods on several multi-label real-world image datasets.