论文标题
adatriplet：自适应梯度三胞胎损失，自动保证金学习法医学图像匹配
AdaTriplet: Adaptive Gradient Triplet Loss with Automatic Margin Learning for Forensic Medical Image Matching
论文作者
论文摘要
本文使用深神经网络（DNNS）解决了法医医学图像匹配（FMIM）的挑战。 FMIM是基于内容的图像检索（CBIR）的特殊情况。与CBIR的一般情况相比，FMIM的主要挑战是，查询图像所属的主题可能受到衰老和进行性退行性疾病的影响，因此很难在主题级别上匹配数据。通常通过最小化排名损失（例如Triplet损耗（TL）），该排名损失（TL）是根据DNN从原始数据提取的图像表示来解决的。尤其是TL在三胞胎上运行：锚点，正（类似于锚）和负（与锚不同）。尽管已显示TL在许多CBIR任务中表现良好，但它仍然有局限性，我们在这项工作中识别和分析。在本文中，我们介绍了（i）adatriplet损失 - TL的扩展，其梯度适应了不同的负样本的不同困难水平，以及（ii）自动核方法方法 - 一种调整基于边际损失的超参数（例如TL）的技术，例如TL和我们提议的损失。根据骨关节炎计划和胸部X射线14数据集，对两个大规模基准进行了我们的结果评估。允许复制本研究的代码已在\ url {https://github.com/oulu-imeds/adatriplet}公开获得。
This paper tackles the challenge of forensic medical image matching (FMIM) using deep neural networks (DNNs). FMIM is a particular case of content-based image retrieval (CBIR). The main challenge in FMIM compared to the general case of CBIR, is that the subject to whom a query image belongs may be affected by aging and progressive degenerative disorders, making it difficult to match data on a subject level. CBIR with DNNs is generally solved by minimizing a ranking loss, such as Triplet loss (TL), computed on image representations extracted by a DNN from the original data. TL, in particular, operates on triplets: anchor, positive (similar to anchor) and negative (dissimilar to anchor). Although TL has been shown to perform well in many CBIR tasks, it still has limitations, which we identify and analyze in this work. In this paper, we introduce (i) the AdaTriplet loss -- an extension of TL whose gradients adapt to different difficulty levels of negative samples, and (ii) the AutoMargin method -- a technique to adjust hyperparameters of margin-based losses such as TL and our proposed loss dynamically. Our results are evaluated on two large-scale benchmarks for FMIM based on the Osteoarthritis Initiative and Chest X-ray-14 datasets. The codes allowing replication of this study have been made publicly available at \url{https://github.com/Oulu-IMEDS/AdaTriplet}.
