A Performance Evaluation of Loss Functions for Deep Face Recognition

Srivastava, Yash; Murali, Vaishnav; Dubey, Shiv Ram

doi:10.1007/978-981-15-8697-2_30

Cited by 39 publications

(23 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The fact that almost all losses perform equally well shows that, contrary to what we thought, metric learning models perform no better than cross entropy, in contrast to other findings (Srivastava et al, 2019) on face verification. One possible explanation is that the AMI dataset may not contain enough examples or classes for these models to exploit.…”

Section: Resultscontrasting

confidence: 96%

“…Other studies have experimented with these methods in different domains with similar characteristics, like speaker verification (Bredin, 2017;Chung et al, 2018;Yadav and Rai, 2018), and even as an enhancement of BERT's sentence representations (Reimers and Gurevych, 2019) for semantic textual similarity. A recent study (Srivastava et al, 2019) has also focused on comparing these methods on face verification, showing that angular margin losses achieve superior performance.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Proceedings of the 5th Workshop on Representation Learning for NLP

2020

View full text Add to dashboard Cite

Existing models for cross-domain named entity recognition (NER) rely on numerous unlabeled corpus or labeled NER training data in target domains. However, collecting data for low-resource target domains is not only expensive but also time-consuming. Hence, we propose a cross-domain NER model that does not use any external resources. We first introduce a Multi-Task Learning (MTL) by adding a new objective function to detect whether tokens are named entities or not. We then introduce a framework called Mixture of Entity Experts (MoEE) to improve the robustness for zero-resource domain adaptation. Finally, experimental results show that our model outperforms strong unsupervised cross-domain sequence labeling models, and the performance of our model is close to that of the state-of-theart model which leverages extensive resources.

show abstract

Section: Resultscontrasting

confidence: 96%

Section: Introductionmentioning

confidence: 99%

Proceedings of the 5th Workshop on Representation Learning for NLP

2020

View full text Add to dashboard Cite

show abstract

“…Cross entropy loss is also known as softmax loss and effectively used in face detection or face recognition task. It can be defined as [20]…”

Section: Cross Entropy Lossmentioning

confidence: 99%

Performance Analysis of Different Loss Function in Face Detection Architectures

Ferdous

Arifeen

Eiko

et al. 2020

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Masked face detection is a challenging task due to the occlusions created by the masks. Recent studies show that deep learning models can achieve effective performance for not only occluded faces but also for unconstrained environments, illuminations or various poses. In this study, we have addressed the problem of occlusion due to wearing masks in masked face detection technique in deep transfer learning method. We have also reviewed the recent deep learning models for face detection and considered VGG16, VGG19, MobileNet and DenseNet as our underlying masked face detection models. Moreover, we have prepared a dataset containing masked face and without mask from 120 individuals and enhanced the dataset using augmentation. After training the deep learning models with our own dataset, we have analysed the performance of the deep learning models for several types of loss functions. From the experiment, it is clear that all the deep learning models perform well in terms of classification losses like categorical cross entropy loss and KL divergence loss.

show abstract

“…These efforts have been focused on two lines of study, on one side, the redesign of the identification loss function, and on the other side, the verification loss functions. The former is composed of Cross-Entropy (CE) loss with softmax output units [4,5,6] combined with a complementary loss such as Ring loss (RL) [7] or Center loss [8], and other studies have been focused on its variants such as Angular Softmax loss (A-Softmax) [9] or Additive Angular Margin loss (ArcFace) [10]. While the latter is based on metric learning approaches as triplet neural network [11,12], contrastive loss [13], partial AUC loss (pAUC) [14] or NeuralPLDA [15].…”

Section: Introductionmentioning

confidence: 99%

Log-Likelihood-Ratio Cost Function as Objective Loss for Speaker Verification Systems

Mingote¹,

Miguel²,

Ortega³

et al. 2021

Interspeech 2021

View full text Add to dashboard Cite

Many recent studies in Speaker Verification (SV) have been focused on the design of the most appropriate training loss function, which plays an important role to improve the recognition ability of the systems. However, the verification loss functions created often do not take into account the performance measures which are used for the final system evaluation. For this reason, this paper presents an alternative approach to optimize the parameters of a neural network using a loss function based on the log-likelihood-ratio cost function (CLLR). This function is an application-independent metric that measures the cost of soft detection decisions over all the operating points. Thus, prior or relevance cost parameters assumptions are not employed to obtain it. Moreover, this metric has a differentiable expression, so no approximation is needed to use it as the objective loss to train a neural network. CLLR function as optimization loss was tested on the RSR2015-Part II database for text-dependent speaker verification, providing competitive results without using score normalization and outperforming other similar loss functions as Cross-Entropy combined with Ring Loss, as well as our previous loss function based on an approximation of the Detection Cost Function (DCF).

show abstract

A Performance Evaluation of Loss Functions for Deep Face Recognition

Cited by 39 publications

References 15 publications

Proceedings of the 5th Workshop on Representation Learning for NLP

Proceedings of the 5th Workshop on Representation Learning for NLP

Performance Analysis of Different Loss Function in Face Detection Architectures

Log-Likelihood-Ratio Cost Function as Objective Loss for Speaker Verification Systems

Contact Info

Product

Resources

About