no code implementations • 9 May 2024 • Marcella Astrid, Muhammad Zaigham Zaheer, Djamila Aouada, Seung-Ik Lee
Due to the rare occurrence of anomalous events, a typical approach to anomaly detection is to train an autoencoder (AE) with normal data only so that it learns the patterns or representations of the normal training data.
no code implementations • 24 Mar 2024 • Marcella Astrid, Muhammad Zaigham Zaheer, Seung-Ik Lee
During test time, since AE is not trained using real anomalies, it is expected to poorly reconstruct the anomalous data.
no code implementations • 19 Mar 2023 • Marcella Astrid, Muhammad Zaigham Zaheer, Seung-Ik Lee
Typically in OCC, an autoencoder (AE) is trained to reconstruct the normal only training data with the expectation that, in test time, it can poorly reconstruct the anomalous data.
no code implementations • 25 Mar 2022 • Muhammad Zaigham Zaheer, Jin Ha Lee, Arif Mahmood, Marcella Astrid, Seung-Ik Lee
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.
no code implementations • 25 Mar 2022 • Muhammad Zaigham Zaheer, Arif Mahmood, Marcella Astrid, 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.
no code implementations • CVPR 2022 • Muhammad Zaigham Zaheer, Arif Mahmood, Muhammad Haris Khan, Mattia Segu, Fisher Yu, Seung-Ik Lee
Video anomaly detection is well investigated in weakly-supervised and one-class classification (OCC) settings.
1 code implementation • 19 Oct 2021 • Marcella Astrid, Muhammad Zaigham Zaheer, Jae-Yeong Lee, Seung-Ik Lee
Typically, to tackle this problem, an autoencoder (AE) is trained to reconstruct the input with training set consisting only of normal data.
Ranked #20 on Anomaly Detection on CUHK Avenue
1 code implementation • 19 Oct 2021 • Marcella Astrid, Muhammad Zaigham Zaheer, Seung-Ik Lee
A popular way to tackle this problem is by utilizing an autoencoder (AE) trained only on normal data.
no code implementations • 24 May 2021 • Jin-ha Lee, Marcella Astrid, Muhammad Zaigham Zaheer, Seung-Ik Lee
However, these are trained with only normal data and at the test time, given abnormal data as input, may often generate normal-looking output.
no code implementations • 30 Apr 2021 • Muhammad Zaigham Zaheer, Jin-ha Lee, Marcella Astrid, Arif Mahmood, Seung-Ik Lee
Learning to detect real-world anomalous events using video-level annotations is a difficult task mainly because of the noise present in labels.
no code implementations • ECCV 2020 • Muhammad Zaigham Zaheer, Arif Mahmood, Marcella Astrid, Seung-Ik Lee
The proposed method obtains83. 03% and 89. 67% frame-level AUC performance on the UCF Crime and ShanghaiTech datasets respectively, demonstrating its superiority over the existing state-of-the-art algorithms.
no code implementations • 27 Aug 2020 • Muhammad Zaigham Zaheer, Arif Mahmood, Hochul Shin, Seung-Ik Lee
Anomalous event detection in surveillance videos is a challenging and practical research problem among image and video processing community.
1 code implementation • Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2020 • Jin-ha Lee, Muhammad Zaigham Zaheer, Marcella Astrid, Seung-Ik Lee
Data augmentation has been proven effective which, by preventing overfitting, can not only enhances the performance of a deep neural network but also leads to a better generalization even with limited dataset.
1 code implementation • CVPR 2020 • Muhammad Zaigham Zaheer, Jin-ha Lee, Marcella Astrid, Seung-Ik Lee
Another possible approach is to use both generator and discriminator for anomaly detection.
Ranked #1 on Anomaly Detection on MNIST-test
no code implementations • 13 Dec 2019 • Jeong-Seon Lim, Marcella Astrid, Hyun-Jin Yoon, Seung-Ik Lee
We propose an object detection method using context for improving accuracy of detecting small objects.
no code implementations • 16 Jan 2018 • Marcella Astrid, Seung-Ik Lee, Beom-Su Seo
One of the method to compress CNNs is compressing the layers iteratively, i. e. by layer-by-layer compression and fine-tuning, with CP-decomposition in convolutional layers.
2 code implementations • 25 Jan 2017 • Marcella Astrid, Seung-Ik Lee
Convolutional Neural Networks (CNNs) has shown a great success in many areas including complex image classification tasks.