Dyn-arcFace: dynamic additive angular margin loss for deep face recognition

Jiao, Jichao; Liu, Weilun; Mo, Yaokai; Jiao, Jian; Deng, Zhongliang; Chen, Xinping

doi:10.1007/s11042-021-10865-5

Cited by 14 publications

(6 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The number of iterations in the Bayesian optimization was set to a total of 50, and the ranges of the values m 1 and m 2 , which must be obtained in Bayesian optimization, were set from 0.5 to 1.0 and from 0.1 to 0.5, respectively. This is because if each margin is smaller or larger than the range, performance degradation occurs [30][31][32]. By controlling the search area of the Bayesian optimization to an appropriate size, we can induce rapid convergence.…”

Section: Figurementioning

confidence: 99%

“…The proposed traffic sign recognition method comprises two principal components: angular margin loss and Bayesian optimization. Angular margin loss is a classification loss employed in metric learning and is a frequently used learning strategy in fields like few-shot learning [30][31][32][33]. The objective of this loss is to optimize the angles between classes in the feature space during the classification process.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Traffic Sign Recognition Based on Bayesian Angular Margin Loss for an Autonomous Vehicle

2023

View full text Add to dashboard Cite

Traffic sign recognition is a pivotal technology in the advancement of autonomous vehicles as it is critical for adhering to country- or region-specific traffic regulations. Defined as an image classification problem in computer vision, traffic sign recognition is a technique that determines the class of a given traffic sign from input data processed by a neural network. Although image classification has been considered a relatively manageable task with the advent of neural networks, traffic sign classification presents its own unique set of challenges due to the similar visual features inherent in traffic signs. This can make designing a softmax-based classifier problematic. To address this challenge, this paper presents a novel traffic sign recognition model that employs angular margin loss. This model optimizes the necessary hyperparameters for the angular margin loss via Bayesian optimization, thereby maximizing the effectiveness of the loss and achieving a high level of classification performance. This paper showcases the impressive performance of the proposed method through experimental results on benchmark datasets for traffic sign classification.

show abstract

Section: Figurementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Traffic Sign Recognition Based on Bayesian Angular Margin Loss for an Autonomous Vehicle

2023

View full text Add to dashboard Cite

show abstract

“…In addition, several lines of research have been improved in various directions based on ArcFace. For example, Dyn-Arcface [46] replaced the flexible margin penalty based on the distance between each class center and the other class centers. ElasticFace loss [47] relaxes the fixed single margin by deploying a random margin drawn from a normal distribution.…”

Section: Introductionmentioning

confidence: 99%

Deep Classification with Linearity-Enhanced Logits to Softmax Function

Shao¹,

Wang

2023

Entropy

View full text Add to dashboard Cite

Recently, there has been a rapid increase in deep classification tasks, such as image recognition and target detection. As one of the most crucial components in Convolutional Neural Network (CNN) architectures, softmax arguably encourages CNN to achieve better performance in image recognition. Under this scheme, we present a conceptually intuitive learning objection function: Orthogonal-Softmax. The primary property of the loss function is to use a linear approximation model that is designed by Gram–Schmidt orthogonalization. Firstly, compared with the traditional softmax and Taylor-Softmax, Orthogonal-Softmax has a stronger relationship through orthogonal polynomials expansion. Secondly, a new loss function is advanced to acquire highly discriminative features for classification tasks. At last, we present a linear softmax loss to further promote the intra-class compactness and inter-class discrepancy simultaneously. The results of the widespread experimental discussion on four benchmark datasets manifest the validity of the presented method. Besides, we want to explore the non-ground truth samples in the future.

show abstract

“…Later, ArcFace [4] proposed additive angular margin by deploying angular penalty margin on the angle between the deep features and their corresponding weights. The great success of softmax loss with penalty margin motivated several works to propose a novel variant of softmax loss [11], [14], [5], [13], [27], [10], [19], [1]. All these solutions achieved notable accuracies on mainstream benchmarks [9], [25], [29], [18] for face recognition.…”

Section: Introductionmentioning

confidence: 99%

“…The proposed loss targets the easy samples at an early stage of training and the hard ones at a later stage of training. Jiao et al [11] proposed Dyn-arcface based on ArcFace loss [4] by replacing the fixed margin value of ArcFace with an adaptive one. The margin value of Dyn-arcface is adjusted based on the distance between each class center and the other class centers.…”

Section: Introductionmentioning

confidence: 99%

ElasticFace: Elastic Margin Loss for Deep Face Recognition

Damer¹,

Kirchbuchner²,

Kuijper³

2021

Preprint

View full text Add to dashboard Cite

Learning discriminative face features plays a major role in building high-performing face recognition models. The recent state-of-the-art face recognition solutions proposed to incorporate a fixed penalty margin on commonly used classification loss function, softmax loss, in the normalized hypersphere to increase the discriminative power of face recognition models, by minimizing the intra-class variation and maximizing the inter-class variation. Marginal softmax losses, such as ArcFace and CosFace, assume that the geodesic distance between and within the different identities can be equally learned using a fixed margin. However, such a learning objective is not realistic for real data with inconsistent interand intra-class variation, which might limit the discriminative and generalizability of the face recognition model. In this paper, we relax the fixed margin constrain by proposing elastic margin loss (ElasticFace) that allows flexibility in the push for class separability. The main idea is to utilize random margin values drawn from a normal distribution in each training iteration. This aims at giving the margin chances to extract and retract to allow space for flexible class separability learning. We demonstrate the superiority of our elastic margin loss over ArcFace and CosFace losses, using the same geometric transformation, on a large set of mainstream benchmarks. From a wider perspective, our ElasticFace has advanced the state-of-the-art face recognition performance on six out of nine mainstream benchmarks. All training codes, pre-trained models, training logs are publicly released 1 .

show abstract

Dyn-arcFace: dynamic additive angular margin loss for deep face recognition

Cited by 14 publications

References 27 publications

Traffic Sign Recognition Based on Bayesian Angular Margin Loss for an Autonomous Vehicle

Traffic Sign Recognition Based on Bayesian Angular Margin Loss for an Autonomous Vehicle

Deep Classification with Linearity-Enhanced Logits to Softmax Function

ElasticFace: Elastic Margin Loss for Deep Face Recognition

Contact Info

Product

Resources

About