Making Reconstruction-based Method Great Again for Video Anomaly Detection Article Swipe

MAKE IMPACT

Yizhou Wang , Can Qin , Yue Bai , Yi Xu , Xu Ma , Yun Fu · YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2301.12048

Anomaly detection in videos is a significant yet challenging problem. Previous approaches based on deep neural networks employ either reconstruction-based or prediction-based approaches. Nevertheless, existing reconstruction-based methods 1) rely on old-fashioned convolutional autoencoders and are poor at modeling temporal dependency; 2) are prone to overfit the training samples, leading to indistinguishable reconstruction errors of normal and abnormal frames during the inference phase. To address such issues, firstly, we get inspiration from transformer and propose ${\textbf S}$patio-${\textbf T}$emporal ${\textbf A}$uto-${\textbf T}$rans-${\textbf E}$ncoder, dubbed as $\textbf{STATE}$, as a new autoencoder model for enhanced consecutive frame reconstruction. Our STATE is equipped with a specifically designed learnable convolutional attention module for efficient temporal learning and reasoning. Secondly, we put forward a novel reconstruction-based input perturbation technique during testing to further differentiate anomalous frames. With the same perturbation magnitude, the testing reconstruction error of the normal frames lowers more than that of the abnormal frames, which contributes to mitigating the overfitting problem of reconstruction. Owing to the high relevance of the frame abnormality and the objects in the frame, we conduct object-level reconstruction using both the raw frame and the corresponding optical flow patches. Finally, the anomaly score is designed based on the combination of the raw and motion reconstruction errors using perturbed inputs. Extensive experiments on benchmark video anomaly detection datasets demonstrate that our approach outperforms previous reconstruction-based methods by a notable margin, and achieves state-of-the-art anomaly detection performance consistently. The code is available at https://github.com/wyzjack/MRMGA4VAD.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2301.12048

PDF

https://arxiv.org/pdf/2301.12048

OA Status

green

Cited By

1

Related Works

10

OpenAlex ID

https://openalex.org/W4318751378

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4318751378

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2301.12048

Digital Object Identifier

Title

Making Reconstruction-based Method Great Again for Video Anomaly Detection

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2023

Year of publication

Publication date

2023-01-28

Full publication date if available

Authors

Yizhou Wang, Can Qin, Yue Bai, Yi Xu, Xu Ma, Yun Fu

List of authors in order

Landing page

https://arxiv.org/abs/2301.12048

Publisher landing page

PDF URL

https://arxiv.org/pdf/2301.12048

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2301.12048

Direct OA link when available

Concepts

Overfitting, Artificial intelligence, Computer science, Anomaly detection, Iterative reconstruction, Pattern recognition (psychology), Convolutional neural network, Computer vision, Deep learning, Algorithm, Artificial neural network

Top concepts (fields/topics) attached by OpenAlex

Cited by

1

Total citation count in OpenAlex

Citations by year (recent)

2024: 1

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload