KappaFace: Adaptive Additive Angular Margin Loss for Deep Face Recognition

• URL: http://arxiv.org/abs/2201.07394v2
• Date: Wed, 6 Dec 2023 07:23:52 GMT
• Title: KappaFace: Adaptive Additive Angular Margin Loss for Deep Face Recognition
• Authors: Chingis Oinar, Binh M. Le, Simon S. Woo
• Abstract summary: We introduce a novel adaptive strategy, called KappaFace, to modulate the relative importance based on class difficultness and imbalance. Experiments conducted on popular facial benchmarks demonstrate that our proposed method achieves superior performance to the state-of-the-art.
• Score: 22.553018305072925
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Feature learning is a widely used method employed for large-scale face recognition. Recently, large-margin softmax loss methods have demonstrated significant enhancements on deep face recognition. These methods propose fixed positive margins in order to enforce intra-class compactness and inter-class diversity. However, the majority of the proposed methods do not consider the class imbalance issue, which is a major challenge in practice for developing deep face recognition models. We hypothesize that it significantly affects the generalization ability of the deep face models. Inspired by this observation, we introduce a novel adaptive strategy, called KappaFace, to modulate the relative importance based on class difficultness and imbalance. With the support of the von Mises-Fisher distribution, our proposed KappaFace loss can intensify the margin's magnitude for hard learning or low concentration classes while relaxing it for counter classes. Experiments conducted on popular facial benchmarks demonstrate that our proposed method achieves superior performance to the state-of-the-art.

Related papers

• CCFace: Classification Consistency for Low-Resolution Face Recognition [12.129404936688752]
  Deep face recognition methods have shown a significant decline in performance when applied to real-world low-resolution benchmarks like TinyFace or SCFace. We propose a novel classification consistency knowledge distillation approach that transfers the learned classifier from a high-resolution model to a low-resolution network. Our proposed method outperforms state-of-the-art approaches on low-resolution benchmarks, with a three percent improvement on TinyFace while maintaining performance on high-resolution benchmarks.
  arXiv  Detail & Related papers  (2023-08-18T01:24:52Z)
• SubFace: Learning with Softmax Approximation for Face Recognition [3.262192371833866]
  SubFace is a softmax approximation method that employs the subspace feature to promote the performance of face recognition. Comprehensive experiments conducted on benchmark datasets demonstrate that our method can significantly improve the performance of vanilla CNN baseline.
  arXiv  Detail & Related papers  (2022-08-24T12:31:08Z)
• SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition [74.13631562652836]
  We propose a novel loss function, named sigmoid-constrained hypersphere loss (SFace) SFace imposes intra-class and inter-class constraints on a hypersphere manifold, which are controlled by two sigmoid gradient re-scale functions respectively. It can make a better balance between decreasing the intra-class distances and preventing overfitting to the label noise, and contributes more robust deep face recognition models.
  arXiv  Detail & Related papers  (2022-05-24T11:54:15Z)
• Federated Learning for Face Recognition with Gradient Correction [52.896286647898386]
  In this work, we introduce a framework, FedGC, to tackle federated learning for face recognition. We show that FedGC constitutes a valid loss function similar to standard softmax.
  arXiv  Detail & Related papers  (2021-12-14T09:19:29Z)
• ElasticFace: Elastic Margin Loss for Deep Face Recognition [6.865656740940772]
  Learning discriminative face features plays a major role in building high-performing face recognition models. Recent state-of-the-art face recognition solutions proposed to incorporate a fixed penalty margin on classification loss function, softmax loss. We propose elastic margin loss (ElasticFace) that allows flexibility in the push for class separability.
  arXiv  Detail & Related papers  (2021-09-20T10:31:50Z)
• SphereFace Revived: Unifying Hyperspherical Face Recognition [57.07058009281208]
  We introduce a unified framework to understand large angular margin in hyperspherical face recognition. Under this framework, we propose an improved variant with substantially better training stability -- SphereFace-R. We show that SphereFace-R is consistently better than or competitive with state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-09-12T17:07:54Z)
• SphereFace2: Binary Classification is All You Need for Deep Face Recognition [57.07058009281208]
  State-of-the-art deep face recognition methods are mostly trained with a softmax-based multi-class classification framework. We propose a novel binary classification training framework, termed SphereFace2. We show that SphereFace2 can consistently outperform current state-of-the-art deep face recognition methods.
  arXiv  Detail & Related papers  (2021-08-03T13:58:45Z)
• Progressive Spatio-Temporal Bilinear Network with Monte Carlo Dropout for Landmark-based Facial Expression Recognition with Uncertainty Estimation [93.73198973454944]
  The performance of our method is evaluated on three widely used datasets. It is comparable to that of video-based state-of-the-art methods while it has much less complexity.
  arXiv  Detail & Related papers  (2021-06-08T13:40:30Z)
• MagFace: A Universal Representation for Face Recognition and Quality Assessment [6.7044749347155035]
  This paper proposes MagFace, a category of losses that learn a universal feature embedding whose magnitude can measure the quality of the given face. Under the new loss, it can be proven that the magnitude of the feature embedding monotonically increases if the subject is more likely to be recognized. In addition, MagFace introduces an adaptive mechanism to learn a well within-class feature by pulling easy samples to class centers while pushing hard samples away.
  arXiv  Detail & Related papers  (2021-03-11T11:58:21Z)
• Loss Function Search for Face Recognition [75.79325080027908]
  We develop a reward-guided search method to automatically obtain the best candidate. Experimental results on a variety of face recognition benchmarks have demonstrated the effectiveness of our method.
  arXiv  Detail & Related papers  (2020-07-10T03:40:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.