Class Aware Auto Encoders for Better Feature Extraction

Islam, Ashhadul; Belhaouari, Samir Brahim

doi:10.1109/icecce52056.2021.9514202

Cited by 3 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to the reconstruction task, several approaches have been proposed to learn better feature representations, e.g. learning both local and global characteristics of the dataset [30], regularization [31,29], and clustering [27,32]. In one-class classification (OCC) problem, similar to [18,15,19,20,21], we employ the reconstruction-based AE to learn the normal data representations using only normal training data.…”

Section: Related Workmentioning

confidence: 99%

PseudoBound: Limiting the anomaly reconstruction capability of one-class classifiers using pseudo anomalies

Astrid,

Zaheer,

Lee

2023

Preprint

View full text Add to dashboard Cite

Due to the rarity of anomalous events, video anomaly detection is typically approached as one-class classification (OCC) problem. 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. However, previous studies have shown that, even trained with only normal data, AEs can often reconstruct anomalous data as well, resulting in a decreased performance. To mitigate this problem, we propose to limit the anomaly reconstruction capability of AEs by incorporating pseudo anomalies during the training of an AE. Extensive experiments using five types of pseudo anomalies show the robustness of our training mechanism towards any kind of pseudo anomaly. Moreover, we demonstrate the effectiveness of our proposed pseudo anomaly based training approach against several existing state-of-the-art (SOTA) methods on three benchmark video anomaly datasets, outperforming all the other reconstruction-based approaches in two datasets and showing the second best performance in the other dataset.

show abstract

Section: Related Workmentioning

confidence: 99%

PseudoBound: Limiting the anomaly reconstruction capability of one-class classifiers using pseudo anomalies

Astrid,

Zaheer,

Lee

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Due to that contractive autoencoder (CAE) adds the Jacobian penalty term to the loss function of AE, CAE has better robustness and extracts potential features more effectively than AE. 33 To simplify the description, the weight parameters and the biases of CAE are referred to as u. Suppose the training set is D n , the loss function of CAE is expressed as:…”

Section: The Sketch Of Ae Cae and Saementioning

confidence: 99%

A fault diagnosis framework for rotating machinery of marine equipment: A semi-supervised learning framework based on contractive stacked autoencoder

Pan

Zhao

2022

Proceedings of the Institution of Mechanical Engineers, Part M:

View full text Add to dashboard Cite

Rotating machinery is one of the key components of marine equipment. Due to the complex and harsh offshore environment, the health status of rotating machinery is more likely to be affected. Therefore, fault diagnosis is of great significance to normal operation and maintenance of rotating machinery in marine equipment. Traditional data-driven fault diagnosis tasks require massive label data for training, and it takes time and manpower to obtain enough label samples. At the same time, it is considered that the noise can interfere with the performance of the fault diagnosis framework. To overcome the above two defects, this paper proposes a fault diagnosis framework based on semi-supervised learning, where the contractive stacked autoencoder (CSA) and the classifier multilayer perceptron (MLP) extract features from unlabeled data and realize fault classification respectively. Compared with the Stacked Autoencoder (SAE)-MLP and Stacked Denoising Autoencoder (SDAE)-MLP frameworks, the proposed learning framework has better fault diagnosis accuracy and robustness.

show abstract

“…Zhang et al [77] introduced a new hybrid model that integrates a Contractive Auto-encoder (CAE) [78] with Biased Singular Value Decomposition (BSVD) [57], termed AutoSVD. The CAE extracts complex, nonlinear feature representations of item information, which are then integrated into SVD to enhance learning and prediction of unknown ratings.…”

Section: Content Datamentioning

confidence: 99%

A Survey of Latent Factor Models for Recommender Systems and Personalization

Shah¹

2021

Preprint

View full text Add to dashboard Cite

<p>Recommender systems aim to personalize the experience of a user and are critical for businesses like retail portals, e-commerce websites, book sellers, streaming movie websites and so on. The earliest personalized algorithms use matrix factorization or matrix completion using algorithms like the singular value decomposition (SVD). There are other more advanced algorithms, like factorization machines, Bayesian personalized ranking (BPR), and a more recent Hebbian graph embeddings (HGE) algorithm. In this work, we implement BPR and HGE and compare our results with SVD, Non-negative matrix factorization (NMF) using the MovieLens dataset.</p>

show abstract

Class Aware Auto Encoders for Better Feature Extraction

Cited by 3 publications

References 8 publications

PseudoBound: Limiting the anomaly reconstruction capability of one-class classifiers using pseudo anomalies

PseudoBound: Limiting the anomaly reconstruction capability of one-class classifiers using pseudo anomalies

A fault diagnosis framework for rotating machinery of marine equipment: A semi-supervised learning framework based on contractive stacked autoencoder

A Survey of Latent Factor Models for Recommender Systems and Personalization

Contact Info

Product

Resources

About