Data Uncertainty Learning in Face Recognition

Chang, J. Morris; Lan, Zhonghao; Cheng, Changmao; Wei, Yichen

doi:10.1109/cvpr42600.2020.00575

Cited by 199 publications

(117 citation statements)

References 32 publications

Supporting

Mentioning

113

Contrasting

Order By: Relevance

“…Aiming at combating the significant negative effects of uncertainty in deep neural networks, uncertainty learning has been getting lots of research attention, which facilitates the reliability assessment and solves risk-based decision-making problems [24]- [26]. In recent years, various frameworks have been proposed to characterize the uncertainty in the model parameters of deep neural networks, referred to as model uncertainty, due to the limited size of training data [27], [28], which can be reduced by collecting more training data [25], [29], [30].…”

Section: B Uncertainty In Deep Learningmentioning

confidence: 99%

“…Meanwhile, another kind of uncertainty in deep learning, referred to as data uncertainty, measures the noise inherent in given training data, and hence cannot be eliminated by having more training data [31]. To combat these two kinds of uncertainty, lots of works on various computer vision tasks, i.e., face recognition [24], semantic segmentation [32], object detection [33], and person reidentification [34], have introduced deep uncertainty learning to improve the robustness of deep learning model and interpretability of discriminant.…”

Section: B Uncertainty In Deep Learningmentioning

confidence: 99%

See 1 more Smart Citation

RCoNet: Deformable Mutual Information Maximization and High-Order Uncertainty-Aware Learning for Robust COVID-19 Detection

Dong

Yang

et al. 2021

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

The novel 2019 Coronavirus (COVID-19) infection has spread worldwide and is currently a major healthcare challenge around the world. Chest computed tomography (CT) and X-ray images have been well recognized to be two effective techniques for clinical COVID-19 disease diagnoses. Due to faster imaging time and considerably lower cost than CT, detecting COVID-19 in chest X-ray (CXR) images is preferred for efficient diagnosis, assessment, and treatment. However, considering the similarity between COVID-19 and pneumonia, CXR samples with deep features distributed near category boundaries are easily misclassified by the hyperplanes learned from limited training data. Moreover, most existing approaches for COVID-19 detection focus on the accuracy of prediction and overlook uncertainty estimation, which is particularly important when dealing with noisy datasets. To alleviate these concerns, we propose a novel deep network named RCoNet k s for robust COVID-19 detection which employs Deformable Mutual Information Maximization (DeIM), Mixed High-order Moment Feature (MHMF), and Multiexpert Uncertainty-aware Learning (MUL). With DeIM, the mutual information (MI) between input data and the corresponding latent representations can be well estimated and maximized to capture compact and disentangled representational characteristics. Meanwhile, MHMF can fully explore the benefits of using high-order statistics and extract discriminative features of complex distributions in medical imaging. Finally, MUL creates multiple parallel dropout networks for each CXR image to evaluate uncertainty and thus prevent performance degradation caused by the noise in the data. The experimental results show that RCoNet k s achieves the state-of-the-art performance on an open-source COVIDx dataset of 15 134 original CXR images across several metrics. Crucially, our method is shown to be more effective than existing methods with the presence of noise in the data.

show abstract

Section: B Uncertainty In Deep Learningmentioning

confidence: 99%

Section: B Uncertainty In Deep Learningmentioning

confidence: 99%

RCoNet: Deformable Mutual Information Maximization and High-Order Uncertainty-Aware Learning for Robust COVID-19 Detection

Dong

Yang

et al. 2021

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

show abstract

“…In terms of face recognition, Y. Shi and A. K. Jain propose probabilistic face embeddings (PFEs) [4] that represent each face image as a Gaussian distribution in the latent space, where the mean and variance of the distribution estimates the most likely feature values and the uncertainty in the feature values, respectively. An extension of PFEs [5] further latent the feature (i.e., mean) and uncertainty (i.e., variance) simultaneously. For object detection, Y.…”

Section: A Uncertainty Learning In Computer Visionmentioning

confidence: 99%

Depth-Aware Object Tracking With a Conditional Variational Autoencoder

Huang

Guo

2021

IEEE Access

View full text Add to dashboard Cite

Object tracking is a fundamental task in computer vision and artificial intelligence. However, state-of-the-art object tracking approaches are still prone to failures and are imprecise when applied to challenging stereos, and their results are generally confidence agonistic. An imprecise deterministic output with low confidence may lead to disastrous consequences and a lack of proof for subsequent operations and human interventions. Deep network training with ambiguous data or the noise inherent in observations (i.e., data uncertainty or aleatoric uncertainty) will result in inherent uncertainties in predictions. In this paper, we exploit probabilistic depth-aware object tracking with a conditional variational autoencoder (CVAE). First, we build a bridge between the Siamese network and the variational autoencoder conditioned with depth images and propose a novel multimodal Bayesian object tracking method. Second, our proposed method yields a complete probability distribution that enables the production of multiple plausible features. Third, the variational autoencoder conditioned by depth images encodes a low-dimensional latent space that conducts depth-aware tracking, which has obvious advantages for challenging tracking stereos. Our proposed tracking method outperformed the state-of-the-art trackers on the VOT 2016, VOT 2018 and VOT 2019

show abstract

“…Modeling data uncertainty is beneficial to deep learning which describes data noise effectively by Gaussian distribution. [17] proposes to model random embeddings for facial recognition in the form of ( ) ( )…”

Section: B Data Uncertainty In Deep Learningmentioning

confidence: 99%

“…These challenges make AAA more complicated. As pointed out in [17] modeling data uncertainty is beneficial in noisy data training [18] [19] [20] [21]. However, recent data uncertainty learning methods treat the modeled multivariate noise independent among components for simplicity, which is not an appropriate assumption for intertwined variables like photographic style.…”

Section: Introductionmentioning

confidence: 99%

Data Covariance Learning in Aesthetic Attributes Assessment

Chen¹

2020

JAMP

View full text Add to dashboard Cite

Data Uncertainty Learning in Face Recognition

Cited by 199 publications

References 32 publications

RCoNet: Deformable Mutual Information Maximization and High-Order Uncertainty-Aware Learning for Robust COVID-19 Detection

RCoNet: Deformable Mutual Information Maximization and High-Order Uncertainty-Aware Learning for Robust COVID-19 Detection

Depth-Aware Object Tracking With a Conditional Variational Autoencoder

Data Covariance Learning in Aesthetic Attributes Assessment

Contact Info

Product

Resources

About