Label embedding asymmetric discrete hashing for efficient cross-modal retrieval

Given the exponential growth of multimedia data, how to swiftly and accurately retrieve information has grown in popularity. Among retrieval techniques, supervised hashing stands out due to its low memory footprint and relatively precise accuracy. Prior theoretical studies often inserted high-order tags into binary code learning, treating them as independent entities. Nevertheless, such approaches frequently neglect the latent category correlations revealed by the label information. Additionally, in terms of optimization, some algorithms employ a bit-by-bit scheme, leading to time-consuming, while others adopt a relaxation-based strategy, producing quantization inaccuracy. To address these issues, we formulate a novel, two-step hashing strategy, termed Label Embedding Asymmetric Discrete Hashing (LEADH). In this study, we provide an asymmetric technique to protect the discrete binary code constraints. Compared with the symmetric model, this method significantly reduces time consumption. In particular, a label-binary mutual mapping architecture is specifically recommended. This model can fully explore and utilize multi-label semantic information to provide better discriminative learned binary codes. Furthermore, to minimize quantization errors, an efficient and effective discrete optimization module based on augmented Lagrangian multipliers is elaborately designed. Extensive experimentation and theoretical study support our model's superiority. Compared to the sub-optimal method, our LEADH achieves an improvement of 2.6%, 1.8%, and 1.1% on Wiki, MIRFlickr, and NUS-WIDE, respectively.