The goal of Unsupervised Anomaly Detection (UAD) is to detect anomalous signals under the condition that only non-anomalous (normal) data is available beforehand. In UAD under Domain-Shift Conditions (UAD-S), data is further exposed to contextual changes that are usually unknown beforehand. Motivated by the difficulties encountered in the UAD-S task presented at the 2021 edition of the Detection and Classification of Acoustic Scenes and Events (DCASE) challenge, we visually inspect Uniform Manifold Approximations and Projections (UMAPs) for log-STFT, log-mel and pretrained Look, Listen and Learn (L3) representations of the DCASE UAD-S dataset. In our exploratory investigation, we look for two qualities, Separability (SEP) and Discriminative Support (DSUP), and formulate several hypotheses that could facilitate diagnosis and developement of further representation and detection approaches. Particularly, we hypothesize that input length and pretraining may regulate a relevant tradeoff between SEP and DSUP. Our code as well as the resulting UMAPs and plots are publicly available.
翻译:未经监督的异常探测(UAD)的目标是在只有非异常(正常)数据才能事先获得的条件下检测异常信号。在Domain-Shift条件下的UAD(UAD-S)中,数据进一步暴露于通常事先不为人知的背景变化中。由于在2021年版的声学场景和事件探测和分类(DCASE)挑战中提出的UAD-S任务中遇到的困难,我们直观地检查对日志-STFT、日志-熔炼和预先培训的 L3 、监听和学习(L3)对DCASE UAD-S数据集的表示(L3 ) 。在我们的探索性调查中,我们寻找两种质量,即可分离性(SEP)和差异性支持(DSUPUP),并拟订若干假设,可以促进诊断和进一步发展进一步的代言和检测方法。特别是,我们假设输入长度和前培训可能调节SEPA和DSUPP之间的相关交易。我们的代码以及由此产生的UMA的公开和图示。