Self-Directed Online Machine Learning for Topology Optimization

Deng, Changyu; Wang, Yizhou; Qin, Can; Lu, Wei

doi:10.21203/rs.3.rs-146826/v1

Cited by 5 publications

(2 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A. Anomaly Detection in Videos a) Reconstruction-based Methods: Thanks to the remarkable success of deep learning [18]- [22], reconstructionbased methods began to emerge several years ago. These approaches learn normal patterns of the training data using deep neural networks like AEs to reconstruct video frames.…”

Section: Related Workmentioning

confidence: 99%

Making Reconstruction-based Method Great Again for Video Anomaly Detection

Wang¹,

Qin²,

Bai³

et al. 2023

Preprint

View full text Add to dashboard Cite

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 Spatio-Temporal Auto-Trans-Encoder, dubbed as 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.

show abstract

Section: Related Workmentioning

confidence: 99%

Making Reconstruction-based Method Great Again for Video Anomaly Detection

Wang¹,

Qin²,

Bai³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Machine learning has been heavily researched and widely used in many areas from object detection (Zou et al, 2019) and speech recognition (Graves et al, 2013) to protein structure prediction (Senior et al, 2020) and engineering design optimization (Deng et al, 2020;Gao and Lu, 2020;Wu et al, 2018). The success is grounded in its powerful capability to learn from a tremendous amount of data.…”

Section: Introductionmentioning

confidence: 99%

Integrating Machine Learning with Human Knowledge

et al. 2020

Self Cite

View full text Add to dashboard Cite

Summary Machine learning has been heavily researched and widely used in many disciplines. However, achieving high accuracy requires a large amount of data that is sometimes difficult, expensive, or impractical to obtain. Integrating human knowledge into machine learning can significantly reduce data requirement, increase reliability and robustness of machine learning, and build explainable machine learning systems. This allows leveraging the vast amount of human knowledge and capability of machine learning to achieve functions and performance not available before and will facilitate the interaction between human beings and machine learning systems, making machine learning decisions understandable to humans. This paper gives an overview of the knowledge and its representations that can be integrated into machine learning and the methodology. We cover the fundamentals, current status, and recent progress of the methods, with a focus on popular and new topics. The perspectives on future directions are also discussed.

show abstract