Abstract
Reconstruction-based approaches to anomaly detection tend to fall short when applied to complex datasets with target classes that possess high inter-class variance. Similar to the idea of self-taught learning used in transfer learning, many domains are rich with similar unlabeled datasets that could be leveraged as a proxy for out-of-distribution samples. In this paper we introduce the latent-insensitive autoencoder (LIS-AE) where unlabeled data from a similar domain are utilized as negative examples to shape the latent layer (bottleneck) of a regular autoencoder such that it is only capable of reconstructing one task. We provide theoretical justification for the proposed training process and loss functions along with an extensive ablation study highlighting important aspects of our model. We test our model in multiple anomaly detection settings presenting quantitative and qualitative analysis showcasing the significant performance improvement of our model for anomaly detection tasks.
Highlights
Detection is a classical machine learning field which is concerned with the identification of in-distribution and out-of-distribution samples that finds applications in numerous fields [1,2]
This issue becomes more relevant in two important settings, namely, when the normal data are relatively complex they require high latent dimensions for good reconstitution, and when anomalies share similar compositional features and are from a close domain to the normal data [9]. To mitigate these issues we present latent-insensitive autoencoder (LIS-AE), a new class of autoencoders where the training process is carried out in two phases
In some cases, minimizing and maximizing the reconstruction loss at the same time becomes contradictory, especially for negative classes that are very similar to the target class. To resolve this issue we introduce another variant with modified first phase loss that ensures that the input of the latent layer is linearly separable for positive and negative examples during the second phase
Summary
Detection is a classical machine learning field which is concerned with the identification of in-distribution and out-of-distribution samples that finds applications in numerous fields [1,2]. It has been observed that this assumption might not hold as standard autoencoders might generalize so well even for anomalies [7,8] This issue becomes more relevant in two important settings, namely, when the normal data are relatively complex they require high latent dimensions for good reconstitution, and when anomalies share similar compositional features and are from a close domain to the normal data [9]. In some cases, minimizing and maximizing the reconstruction loss at the same time becomes contradictory, especially for negative classes that are very similar to the target class To resolve this issue we introduce another variant with modified first phase loss that ensures that the input of the latent layer is linearly separable for positive and negative examples during the second phase. Details of architecture, training process, theoretical analysis, and experiments are discussed in detail
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
