Marcella Astrid

Marcella Astrid

Auto-generated profile, based on publicly available information

Marcella Astrid

Department of Artificial Intelligence University of Science and Technology Daejeon Republic of Korea

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 May 2023 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
MZMuhammad Zaigham Zaheer
Muhammad Zaigham Zaheer
AMArif Mahmood
Arif Mahmood
MAMarcella Astrid
Marcella Astrid
SLSeung-Ik Lee
Seung-Ik Lee
Formulating learning systems for the detection of real-world anomalous events using only video-level labels is a challenging task mainly due to the presence of noisy labels as well as the rare occurrence of anomalous events in the training data. We propose a weakly supervised anomaly detection system that has multiple contributions including a random batch selection mechanism to reduce interbatch correlation and a normalcy suppression block (NSB) which learns to minimize anomaly scores over normal regions of a video by utilizing the overall information available in a training batch. In addition, a clustering loss block (CLB) is proposed to mitigate the label noise and to improve the representation learning for the anomalous and normal regions. This block encourages the backbone network to produce two distinct feature clusters representing normal and anomalous events. An extensive analysis of the proposed approach is provided using three popular anomaly detection datasets including UCF-Crime, ShanghaiTech, and UCSD Ped2. The experiments demonstrate the superior anomaly detection capability of our approach.

12 September 2022 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
MZMuhammad Zaigham Zaheer
Muhammad Zaigham Zaheer
JLJin-Ha Lee
Jin-Ha Lee
AMArif Mahmood
Arif Mahmood
MAMarcella Astrid
Marcella Astrid
SLSeung-Ik Lee
Seung-Ik Lee
Recently, anomaly scores have been formulated using reconstruction loss of the adversarially learned generators and/or classification loss of discriminators. Unavailability of anomaly examples in the training data makes optimization of such networks challenging. Attributed to the adversarial training, performance of such models fluctuates drastically with each training step, making it difficult to halt the training at an optimal point. In the current study, we propose a robust anomaly detection framework that overcomes such instability by transforming the fundamental role of the discriminator from identifying real vs. fake data to distinguishing good vs. bad quality reconstructions. For this purpose, we propose a method that utilizes the current state as well as an old state of the same generator to create good and bad quality reconstruction examples. The discriminator is trained on these examples to detect the subtle distortions that are often present in the reconstructions of anomalous data. In addition, we propose an efficient generic criterion to stop the training of our model, ensuring elevated performance. Extensive experiments performed on six datasets across multiple domains including image and video based anomaly detection, medical diagnosis, and network security, have demonstrated excellent performance of our approach.

7 August 2018 in ETRI Journal
Verified
Journal Article
Open access
PDF file
MAMarcella Astrid
Marcella Astrid
SLSeung-Ik Lee
Seung-Ik Lee
The application of deep neural networks (DNNs) to connect the world with cyber physical systems (CPSs) has attracted much attention. However, DNNs require a large amount of memory and computational cost, which hinders their use in the relatively low‐end smart devices that are widely used in CPSs. In this paper, we aim to determine whether DNNs can be efficiently deployed and operated in low‐end smart devices. To do this, we develop a method to reduce the memory requirement of DNNs and increase the inference speed, while maintaining the performance (for example, accuracy) close to the original level. The parameters of DNNs are decomposed using a hybrid of canonical polyadic–singular value decomposition, approximated using a tensor power method, and fine‐tuned by performing iterative one‐shot hybrid fine‐tuning to recover from a decreased accuracy. In this study, we evaluate our method on frequently used networks. We also present results from extensive experiments on the effects of several fine‐tuning methods, the importance of iterative fine‐tuning, and decomposition techniques. We demonstrate the effectiveness of the proposed method by deploying compressed networks in smartphones.

15 July 2021
Verified
Book Chapter
Closed access
PDF file
JLJin-Ha Lee
Jin-Ha Lee
MAMarcella Astrid
Marcella Astrid
MZMuhammad Zaigham Zaheer
Muhammad Zaigham Zaheer
SLSeung-Ik Lee
Seung-Ik Lee

29 October 2023 in ETRI Journal
Verified
Journal Article
Closed access
MAMarcella Astrid
Marcella Astrid
SLSeung-Ik Lee
Seung-Ik Lee