Evolution of heterogeneous ensembles through dynamic particle swarm optimization for video-based face recognition

Connolly, Jean-François; Granger, Éric; Sabourin, Robert

doi:10.1016/j.patcog.2011.12.016

Cited by 29 publications

(30 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It allows to evolve an ensemble heterogeneous multiclass classifiers from new data, using a LTM to store validation samples for fitness estimation and to stop training epochs. This approach reduces the effect of knowledge corruption [1]. Another adaptive MCS for FRiVS is composed of an ensemble of binary 2-class classifiers per individual, a DPSO module and a LTM.…”

Section: Adaptive Face Recognition In Videomentioning

confidence: 99%

“…The PFAM classifier combines the Fuzzy ARTMAP learning to encode category prototypes and update centers of mass of estimated class distributions [14]. A DPSO learning strategy was used for base classifiers generation and hyperparameter optimization [1]. The value of relevance measures produced by the ensembles are presented on Fig.…”

Section: Adaptive Face Recognition In Videomentioning

confidence: 99%

“…Given an individual of interest, the operator of a humancentric decision support system for person re-identification captures reference facial trajectories 1 corresponding to an individual appearing in video feeds, and designs a facial model (e.g. templates or statistical representation) to be stored in a gallery.…”

Section: Introductionmentioning

confidence: 99%

“…Finally, changes in the physiognomy of individuals lead to changes in the classification environment, and facial models may not be representative of all operational conditions, thus, exhibiting poor performance. Updating facial models has been shown to improve or maintain a high level of performance over various operating conditions [1,3]. This paper is focused on adaptive video-to-video FR using multi-classifier systems (MCSs).…”

Section: Introductionmentioning

confidence: 99%

“…It is assumed that faces cap-tured within trajectories (obtained from post-analysis of video feeds) are used for supervised incremental learning of facial models. Although adaptive ensembles have been applied to face modeling [1,3,18], they require the storage of reference validation samples in a long term memory (LTM) to preserve accuracy. One challenge for practical implementation is bounding the growing number of reference samples collected over several updates.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

An Individual-Specific Strategy for Management of Reference Data in Adaptive Ensembles for Person Re-Identification

De-la-Torre¹,

Granger²,

Sabourin³

et al. 2013

5th International Conference on Imaging for Crime Detection and Prevention (ICDP 2013)

View full text Add to dashboard Cite

In video surveillance, person re-identification refers to recognizing individuals of interest from faces captured across a network of video cameras. Face recognition in such applications is challenging because faces are captured with limited spatial and temporal constraints. In addition, facial models for recognition are commonly designed using limited reference samples from faces captured under specific conditions. Given new reference samples, updating facial models may allow maintaining a high level of performance over time. Although adaptive ensembles have been successfully applied to robust modeling of an individual's face, reference data samples must be stored for validation. In this paper, a memory management strategy based on Kullback-Leiber (KL) divergence is proposed to rank and select the most relevant validation samples over time in adaptive individual-specific ensembles. When new reference data becomes available for an individual, updates to the corresponding ensembles are validated using a mixture of new and previously-stored samples. Only the samples with the highest KL divergence are preserved in memory for future adaptations. The strategy is compared with reference classifiers using videos from the FIA data set. Simulation results show that the proposed strategy tends to select samples of statistically different subjects (so-called "wolfs") for validation, thereby reducing the number of samples per individual by up to 80%, yet maintaining a high level of performance.

show abstract

Section: Adaptive Face Recognition In Videomentioning

confidence: 99%

Section: Adaptive Face Recognition In Videomentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

An Individual-Specific Strategy for Management of Reference Data in Adaptive Ensembles for Person Re-Identification

De-la-Torre¹,

Granger²,

Sabourin³

et al. 2013

5th International Conference on Imaging for Crime Detection and Prevention (ICDP 2013)

View full text Add to dashboard Cite

show abstract

Prediction of liquid ammonia yield using a novel deep learning‐based heterogeneous pruning ensemble model

Dai

Yang

Zhang

et al. 2020

Asia-Pacific J Chem Eng

View full text Add to dashboard Cite

Liquid ammonia yield is the main index characterizing the process output of ammonia synthesis, the prediction of which is crucial for process control and optimization. However, the industrial process of ammonia synthesis involves multiple variables and strong nonlinearity, making it difficult to be accurately predicted using conventional mechanism‐driven model, or a certain type of data‐driven model. Therefore, a deep learning‐based heterogeneous pruning ensemble (DL‐HPE) model is proposed to overcome the limitations of conventional models. In this model, a “VDiv” pruning strategy that trades off diversity and accuracy is proposed and successfully applied to select the optimal subset from nine representative base models. Finally, the deep learning is employed to integrate the outputs of the involving models to generate the final prediction. The DL‐HPE method was applied to modeling the UCI standard dataset and the historical dataset collected from an ammonia plant in China. The results show that the method is superior to single model or other ensemble models both in accuracy and in robustness.

show abstract

Different Applications of PSO

Badar

2021

International Series in Operations Research &Amp; Management Science

View full text Add to dashboard Cite

Evolution of heterogeneous ensembles through dynamic particle swarm optimization for video-based face recognition

Cited by 29 publications

References 42 publications

An Individual-Specific Strategy for Management of Reference Data in Adaptive Ensembles for Person Re-Identification

An Individual-Specific Strategy for Management of Reference Data in Adaptive Ensembles for Person Re-Identification

Prediction of liquid ammonia yield using a novel deep learning‐based heterogeneous pruning ensemble model

Different Applications of PSO

Contact Info

Product

Resources

About