Domain Balancing: Face Recognition on Long-Tailed Domains

Cao, Dong; Zhu, Xiangyu; Huang, Xingyu; Guo, Jianzhu; Lei, Zhen

doi:10.48550/arxiv.2003.13791

Cited by 2 publications

(2 citation statements)

References 34 publications

(47 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most existing FR works trained networks on global face images (Deng et al 2019;Cao et al 2020). However, they may suffer from performance drops when tackling faces taken in challenging cases.…”

Section: Face Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

CQA-Face: Contrastive Quality-Aware Attentions for Face Recognition

Wang

Guo

2022

AAAI

View full text Add to dashboard Cite

Few existing face recognition (FR) models take local representations into account. Although some works achieved this by extracting features on cropped parts around face landmarks, landmark detection may be inaccurate or even fail in some extreme cases. Recently, without relying on landmarks, attention-based networks can focus on useful parts automatically. However, there are two issues: 1) It is noticed that these approaches focus on few facial parts, while missing other potentially discriminative regions. This can cause performance drops when emphasized facial parts are invisible under heavy occlusions (e.g. face masks) or large pose variations; 2) Different facial parts may appear at various quality caused by occlusion, blur, or illumination changes. In this paper, we propose contrastive quality-aware attentions, called CQA-Face, to address these two issues. First, a Contrastive Attention Learning (CAL) module is proposed, pushing models to explore comprehensive facial parts. Consequently, more useful parts can help identification if some facial parts are invisible. Second, a Quality-Aware Network (QAN) is developed to emphasize important regions and suppress noisy parts in a global scope. Thus, our CQA-Face model is developed by integrating the CAL with QAN, which extracts diverse quality-aware local representations. It outperforms the state-of-the-art methods on several benchmarks, demonstrating its effectiveness and usefulness.

show abstract

Section: Face Recognitionmentioning

confidence: 99%

“…Previous works can be divided into two categories: global-based approaches and local-based methods. The former learns features on global face images (Deng et al 2019;Cao et al 2020). However, they rarely consider representations on local patches to improve discrimination of face features.…”

Section: Introductionmentioning

confidence: 99%

CQA-Face: Contrastive Quality-Aware Attentions for Face Recognition

Wang

Guo

2022

AAAI

View full text Add to dashboard Cite

show abstract

Unsupervised Eyeglasses Removal in the Wild

Hu¹,

Zheng²,

Ping³

et al. 2019

Preprint

View full text Add to dashboard Cite

Eyeglasses removal is challenging in removing different kinds of eyeglasses, e.g., rimless glasses, full-rim glasses and sunglasses, and recovering appropriate eyes. Due to the significant visual variants, the conventional methods lack scalability. Most existing works focus on the frontal face images in the controlled environment such as laboratory and need to design specific systems for different eyeglass types. To address the limitation, we propose a unified eyeglass removal model called Eyeglasses Removal Generative Adversarial Network (ERGAN), which could handle different types of glasses in the wild. The proposed method does not depend on the dense annotation of eyeglasses location but benefits from the large-scale face images with weak annotations. Specifically, we study the two relevant tasks simultaneously, i.e., removing and wearing eyeglasses. Given two facial images with and without eyeglasses, the proposed model learns to swap the eye area in two faces. The generation mechanism focuses on the eye area and invades the difficulty of generating a new face. In the experiment, we show the proposed method achieves a competitive removal quality in terms of realism and diversity. Furthermore, we evaluate our method on several subsequent tasks, such as face verification and facial expression recognition. The experiment shows that our method could serve as a pre-processing method for these tasks.

show abstract

Domain Balancing: Face Recognition on Long-Tailed Domains

Cited by 2 publications

References 34 publications

CQA-Face: Contrastive Quality-Aware Attentions for Face Recognition

CQA-Face: Contrastive Quality-Aware Attentions for Face Recognition

Unsupervised Eyeglasses Removal in the Wild

Contact Info

Product

Resources

About