用对比学习提升弹壳来源鉴定准确率，优于现有方法。
Deep Learning for Forensic Identification of Source
- 采用对比神经网络学习弹壳间相似性得分。
- 在E3数据集上达到0.892的ROC AUC，高于CMC的0.867。
- 对网络结构变化不敏感，适合实际司法应用。
我们使用对比神经网络，在NBIDE数据集的144个弹壳上，针对常见但未知来源问题学习有用的相似性评分。该问题是法医鉴定中的典型难题：判断两个物体是否来自同一来源（如两枚弹壳是否由同一枪支发射）。相似性评分常用于此类证据的解释。我们直接将结果与最先进的算法Congruent Matching Cells（CMC）进行比较。在包含2967个弹壳的E3数据集上，对比学习取得了0.892的ROC AUC，而CMC为0.867。我们还进行了消融实验，改变神经网络的宽度或深度，结果显示对比网络性能对架构变化具有一定鲁棒性。本研究部分旨在推动对比学习获得的相似性评分应用于标准证据解释方法，如基于评分的似然比分析。
原文摘要 · Abstract (English)
We used contrastive neural networks to learn useful similarity scores between the 144 cartridge casings in the NBIDE dataset, under the common-but-unknown source paradigm. The common-but-unknown source problem is a problem archetype in forensics where the question is whether two objects share a common source (e.g. were two cartridge casings fired from the same firearm). Similarity scores are often used to interpret evidence under this paradigm. We directly compared our results to a state-of-the-art algorithm, Congruent Matching Cells (CMC). When trained on the E3 dataset of 2967 cartridge casings, contrastive learning achieved an ROC AUC of 0.892. The CMC algorithm achieved 0.867. We also conducted an ablation study where we varied the neural network architecture; specifically, the network's width or depth. The ablation study showed that contrastive network performance results are somewhat robust to the network architecture. This work was in part motivated by the use of similarity scores attained via contrastive learning for standard evidence interpretation methods such as score-based likelihood ratios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。