Subspace selection to suppress confounding source domain information in AAM transfer learning

Asgarian, Azin; Ashraf, Ahmed Bilal; Fleet, David J.; Taati, Babak

doi:10.1109/btas.2017.8272730

Cited by 4 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While several effective transfer learning techniques are available for AMM models [24], [25], such methods are typically used when only a handful of training images from the target domain are available, e.g. as low as 5 target training images [24], [26]. In our case, with the availability of a few hundred training images, it was possible to fully retrain the AAM model from scratch.…”

Section: Retraining and Fine-tuningmentioning

confidence: 99%

Algorithmic Bias in Clinical Populations—Evaluating and Improving Facial Analysis Technology in Older Adults With Dementia

et al. 2019

Self Cite

View full text Add to dashboard Cite

The need for the automated facial expression analysis arises in various clinical settings involving mental and physical health assessment of older adults. However, the effect of age (young versus old) and ability (healthy versus physical or cognitive impairment) on the performance of available methods has not yet been investigated. In this paper, we demonstrate a bias affecting the performance of common facial landmark detection and expression recognition algorithms on the faces of older adults with dementia. We also investigate the ways of mitigating this bias via the addition of representative training examples. Results show that landmark placement is less accurate when tested on the faces of individuals with dementia as compared to older adults who are cognitively healthy. Retraining or fine-tuning the methods with images of older adults' faces improves the performance significantly, but the gap between older adults with versus without dementia persists. As the interest in using facial analysis methods in clinical applications grows, results of this study: 1) highlight the limitations of the existing models when applied to clinical populations and 2) shed light on methods of addressing these limitations as well as the need to develop algorithms designed to be fair with respect to variables such as age and ability. INDEX TERMS Facial analysis, older adults, dementia, facial landmark detection, facial action units.

show abstract

Section: Retraining and Fine-tuningmentioning

confidence: 99%

Algorithmic Bias in Clinical Populations—Evaluating and Improving Facial Analysis Technology in Older Adults With Dementia

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…We compare the performance of different methods on the cognitively healthy older adult subset (H) versus the dementia subset (D) of T f and T p in terms of the convergence rate. To measure the convergence rate, we use its standard definition in the literature [2,8,32] as the percentage of test examples that converge to the ground truth landmark points given a tolerance in the root mean squared (RMS) fitting error (here, 5% of the face diagonal).…”

Section: Discussionmentioning

confidence: 99%

Limitations and Biases in Facial Landmark Detection -- An Empirical Study on Older Adults with Dementia

Asgarian¹,

Zhao²,

Ashraf³

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

Accurate facial expression analysis is an essential step in various clinical applications that involve physical and mental health assessments of older adults (e.g. diagnosis of pain or depression). Although remarkable progress has been achieved toward developing robust facial landmark detection methods, state-of-the-art methods still face many challenges when encountering uncontrolled environments, different ranges of facial expressions, and different demographics of population. A recent study has revealed that the health status of individuals can also affect the performance of facial landmark detection methods on front views of faces. In this work, we investigate this matter in a much greater context using seven facial landmark detection methods. We perform our evaluation not only on frontal faces but also on profile faces and in various regions of the face. Our results shed light on limitations of the existing methods and challenges of applying these methods in clinical settings by indicating: 1) a significant difference between the performance of state-of-the-art when tested on the profile or frontal faces of individuals with vs. without dementia; 2) insights on the existing bias for all regions of the face; and 3) the presence of this bias despite re-training/fine-tuning with various configurations of six datasets.

show abstract

“…Here (x) shows the error for each sample and α is a hyper-parameter that controls the overall relative importance between source and target samples. Source sample weights {w xj = PT (xj ) PS (xj ) | j ∈ {1, ..., N S }} play a major role in instance-based transfer learning methods, as they control the individual effect of source samples (Asgarian et al, 2017). We describe different weighting approaches including our five baselines models and our proposed weighting strategy in the following.…”

Section: Transfer Learningmentioning

confidence: 99%

Prediction of Workplace Injuries

Sadeqi¹,

Asgarian²,

Sibilia³

2019

Preprint

Self Cite

View full text Add to dashboard Cite

Workplace injuries result in substantial human and financial losses. As reported by the International Labour Organization (ILO), there are more than 374 million work-related injuries reported every year. In this study, we investigate the problem of injury risk prediction and prevention in a work environment. While injuries represent a significant number across all organizations, they are rare events within a single organization. Hence, collecting a sufficiently large dataset from a single organization is extremely difficult. In addition, the collected datasets are often highly imbalanced which increases the problem difficulty. Finally, risk predictions need to provide additional context for injuries to be prevented. We propose and evaluate the following for a complete solution: 1) several ensemble-based resampling methods to address the class imbalance issues, 2) a novel transfer learning approach to transfer the knowledge across organizations, and 3) various techniques to uncover the association and causal effect of different variables on injury risk, while controlling for relevant confounding factors.

show abstract

Subspace selection to suppress confounding source domain information in AAM transfer learning

Cited by 4 publications

References 18 publications

Algorithmic Bias in Clinical Populations—Evaluating and Improving Facial Analysis Technology in Older Adults With Dementia

Algorithmic Bias in Clinical Populations—Evaluating and Improving Facial Analysis Technology in Older Adults With Dementia

Limitations and Biases in Facial Landmark Detection -- An Empirical Study on Older Adults with Dementia

Prediction of Workplace Injuries

Contact Info

Product

Resources

About