发表机构
aFraunhofer Institute for Applied
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究语义哈希方法，提出动态语义通道哈希（DSCH）损失函数，通过动态调整语义通道避免损失景观不连续性，采用考虑平局的mAP评估，实验表明DSCH训练的模型在多任务中表现优异，优于其他现有损失函数。
AI 中文摘要
近年来，用于生成短二进制哈希码以在高维数据空间中进行高效近似最近邻搜索的语义哈希方法受到广泛关注。基于深度学习的方法比传统的手动特征工程方法具有更好的语义捕捉能力。此前工作研究了汉明空间的性质并引入了基于预定义语义通道的损失函数，但该公式使损失景观出现不连续性，优化变得复杂。基于此，我们提出了动态语义通道哈希（DSCH）损失函数，使用动态大小和位置的语义通道来避免损失景观的不连续性。此外，我们支持使用考虑平局的平均平均精度（mAP）作为评估指标。在两个流行数据集上进行的多个实验设置表明，使用DSCH目标进行训练优于使用其他现有损失函数。在40个跨模态和模态内检索任务中的35个任务中，使用DSCH训练的模型在所有四个测试哈希码长度上均取得了显著更高的考虑平局的mAP分数。
英文摘要
Semantic hashing methods for generating short binary hash codes that allow efficient approximate nearest neighbor search in high-dimensional data spaces have gained extensive consideration in recent years. Deep learning-based methods offer better semantic capturing capabilities than traditional approaches relying on manual feature engineering. Moreover, they enable a data-driven approach to semantic hashing across diverse data modalities, yielding high-quality cross-modal hash codes within a shared Hamming space. Previous work investigated the properties of this Hamming space and introduced a loss function based on predefined so-called semantic channels with fixed width and Hamming distances derived from label similarities. However, this formulation also introduced discontinuities into the loss landscape, complicating optimization. Based on these observations, we propose a newly designed loss function, Dynamic Semantic Channel Hashing (DSCH), using dynamically sized and positioned semantic channels in order to avoid loss landscape discontinuities. Furthermore, we endorse the use of tie-aware Mean Average Precision (mAP) as evaluation metric as it addresses the ambiguity in sample retrieval ordering, which emerges from the discreteness of hash code distances. Finally, multiple experimental settings conducted on two popular datasets and incorporating two different model architectures provide strong evidence that training using the DSCH objective outperforms training using other state-of-the-art loss functions. In a total of 35 out of 40 cross-modal and intra-modal retrieval tasks, models trained with DSCH achieve significantly higher tie-aware mAP scores across all four tested hash code lengths, showing compelling results across model architecture and used dataset. The mAP score uplifts are consistent and amount up to 1.75 percentage points compared to the respective second best.
Comments12 pages, 3 figures, 9 tables
