Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308235887> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4308235887 abstract "Anomaly Detection (AD) aims to find defective patterns or abnormal samples among data, and has been a hot research topic due to various real-world applications. While various AD methods have been proposed, most of them assume the availability of a clean (anomaly-free) training set, which however may be hard to guarantee in many real-world industry applications. This motivates us to investigate Unsupervised Anomaly Detection (UAD) in which the training set includes both normal and abnormal samples. In this paper, we address the UAD problem by proposing a Self-Training and Knowledge Distillation (STKD) model. STKD combats anomalies in the training set by iteratively alternating between excluding samples of high anomaly probabilities and training the model with the purified training set. Despite that the model is trained with a cleaner training set, the inevitably existing anomalies may still cause negative impact. STKD alleviates this by regularizing the model to respond similarly to a teacher model which has not been trained with noisy data. Experiments show that STKD consistently produces more robust performance with different levels of anomalies." @default.
- W4308235887 created "2022-11-09" @default.
- W4308235887 creator A5044740674 @default.
- W4308235887 creator A5051363890 @default.
- W4308235887 creator A5074865219 @default.
- W4308235887 creator A5075993453 @default.
- W4308235887 date "2022-10-16" @default.
- W4308235887 modified "2023-10-14" @default.
- W4308235887 title "Unsupervised Anomaly Detection with Self-Training and Knowledge Distillation" @default.
- W4308235887 cites W1635340334 @default.
- W4308235887 cites W1986332411 @default.
- W4308235887 cites W1995443851 @default.
- W4308235887 cites W1996516822 @default.
- W4308235887 cites W1998025795 @default.
- W4308235887 cites W2023639956 @default.
- W4308235887 cites W2074506142 @default.
- W4308235887 cites W2129281431 @default.
- W4308235887 cites W2132870739 @default.
- W4308235887 cites W2194775991 @default.
- W4308235887 cites W2743138268 @default.
- W4308235887 cites W2914570111 @default.
- W4308235887 cites W2948982773 @default.
- W4308235887 cites W2963049059 @default.
- W4308235887 cites W3035160371 @default.
- W4308235887 cites W3121084473 @default.
- W4308235887 cites W3166166117 @default.
- W4308235887 doi "https://doi.org/10.1109/icip46576.2022.9897777" @default.
- W4308235887 hasPublicationYear "2022" @default.
- W4308235887 type Work @default.
- W4308235887 citedByCount "0" @default.
- W4308235887 crossrefType "proceedings-article" @default.
- W4308235887 hasAuthorship W4308235887A5044740674 @default.
- W4308235887 hasAuthorship W4308235887A5051363890 @default.
- W4308235887 hasAuthorship W4308235887A5074865219 @default.
- W4308235887 hasAuthorship W4308235887A5075993453 @default.
- W4308235887 hasConcept C119857082 @default.
- W4308235887 hasConcept C121332964 @default.
- W4308235887 hasConcept C124101348 @default.
- W4308235887 hasConcept C12997251 @default.
- W4308235887 hasConcept C153180895 @default.
- W4308235887 hasConcept C153294291 @default.
- W4308235887 hasConcept C154945302 @default.
- W4308235887 hasConcept C177264268 @default.
- W4308235887 hasConcept C178790620 @default.
- W4308235887 hasConcept C185592680 @default.
- W4308235887 hasConcept C199360897 @default.
- W4308235887 hasConcept C204030448 @default.
- W4308235887 hasConcept C26873012 @default.
- W4308235887 hasConcept C2777211547 @default.
- W4308235887 hasConcept C41008148 @default.
- W4308235887 hasConcept C51632099 @default.
- W4308235887 hasConcept C58489278 @default.
- W4308235887 hasConcept C739882 @default.
- W4308235887 hasConceptScore W4308235887C119857082 @default.
- W4308235887 hasConceptScore W4308235887C121332964 @default.
- W4308235887 hasConceptScore W4308235887C124101348 @default.
- W4308235887 hasConceptScore W4308235887C12997251 @default.
- W4308235887 hasConceptScore W4308235887C153180895 @default.
- W4308235887 hasConceptScore W4308235887C153294291 @default.
- W4308235887 hasConceptScore W4308235887C154945302 @default.
- W4308235887 hasConceptScore W4308235887C177264268 @default.
- W4308235887 hasConceptScore W4308235887C178790620 @default.
- W4308235887 hasConceptScore W4308235887C185592680 @default.
- W4308235887 hasConceptScore W4308235887C199360897 @default.
- W4308235887 hasConceptScore W4308235887C204030448 @default.
- W4308235887 hasConceptScore W4308235887C26873012 @default.
- W4308235887 hasConceptScore W4308235887C2777211547 @default.
- W4308235887 hasConceptScore W4308235887C41008148 @default.
- W4308235887 hasConceptScore W4308235887C51632099 @default.
- W4308235887 hasConceptScore W4308235887C58489278 @default.
- W4308235887 hasConceptScore W4308235887C739882 @default.
- W4308235887 hasLocation W43082358871 @default.
- W4308235887 hasOpenAccess W4308235887 @default.
- W4308235887 hasPrimaryLocation W43082358871 @default.
- W4308235887 hasRelatedWork W2042251007 @default.
- W4308235887 hasRelatedWork W2063729131 @default.
- W4308235887 hasRelatedWork W2065643612 @default.
- W4308235887 hasRelatedWork W2076520961 @default.
- W4308235887 hasRelatedWork W2110365568 @default.
- W4308235887 hasRelatedWork W2619477556 @default.
- W4308235887 hasRelatedWork W2984111956 @default.
- W4308235887 hasRelatedWork W4308235887 @default.
- W4308235887 hasRelatedWork W4311571903 @default.
- W4308235887 hasRelatedWork W2130317780 @default.
- W4308235887 isParatext "false" @default.
- W4308235887 isRetracted "false" @default.
- W4308235887 workType "article" @default.