Image retrieval has become an increasingly appealing technique with broad multimedia application prospects, where deep hashing serves as the dominant branch towards low storage and efficient retrieval. In this paper, we carried out in-depth investigations on metric learning in deep hashing for establishing a powerful metric space in multi-label scenarios, where the pair loss suffers high computational overhead and converge difficulty, while the proxy loss is theoretically incapable of expressing the profound label dependencies and exhibits conflicts in the constructed hypersphere space. To address the problems, we propose a novel metric learning framework with Hybrid Proxy-Pair Loss (HyP$^2$ Loss) that constructs an expressive metric space with efficient training complexity w.r.t. the whole dataset. The proposed HyP$^2$ Loss focuses on optimizing the hypersphere space by learnable proxies and excavating data-to-data correlations of irrelevant pairs, which integrates sufficient data correspondence of pair-based methods and high-efficiency of proxy-based methods. Extensive experiments on four standard multi-label benchmarks justify the proposed method outperforms the state-of-the-art, is robust among different hash bits and achieves significant performance gains with a faster, more stable convergence speed. Our code is available at https://github.com/JerryXu0129/HyP2-Loss.
翻译:图像检索已成为一种越来越具有吸引力的技术,具有广泛的多媒体应用前景,深的散列成为低存储和高效检索的主要分支。在本文中,我们深入调查了深度散列的计量学习,以在多标签情景中建立一个强大的衡量空间,即双胞胎损失在计算上有着很高的间接费用和趋同的困难,而代用损失在理论上无法表达构建的超视距空间中深刻的标签依赖性和物证冲突。为了解决问题,我们提议了一个新型的衡量学习框架,即混合代用保单损失(HyP$2$2$Loss)(HyP$2$Loss),以高效的培训复杂性(w.r.t.t.)构建一个直观的计量空间。拟议的HP$2$侧重于优化超视空间,通过可理解的准轴心和挖掘不相干对双胞胎的数据对数据与数据之间的关联。为了解决问题,我们提议的四个标准多标签基准的大规模实验证明,这比标准方法要优于全方位(W.r.r.t.t.t.h.h)/rxxx