Improve Cross-Domain Face Recognition with IBN-block

Qing, Yangchun; Zhao, Yafei; Shi, Yongjie; Chen, Dan; Lin, Yining; Peng, Yao

doi:10.1109/bigdata.2018.8622251

Cited by 4 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li et al [58] remove bias by taking the mean and standard deviation from the target domain as batch normalization parameters. Qing et al [59] combine instance and batch normalization (IBN) to improve cross-domain recognition. Nam et al [60] propose batch-instance normalization (BIN), summing instance and batch normalization with an optimal ratio; they thus yield superior results by learning the ratio between two operators.…”

Section: Domain Adaptation For Face Recognitionmentioning

confidence: 99%

Mitigating Domain Mismatch in Face Recognition Using Style Matching

Lin¹,

Wu²

2021

Preprint

View full text Add to dashboard Cite

Despite outstanding performance on public benchmarks, face recognition still suffers due to domain mismatch between training (source) and testing (target) data. Furthermore, these domains are not shared classes, which complicates domain adaptation. Since this is also a fine-grained classification problem which does not strictly follow the low-density separation principle, conventional domain adaptation approaches do not resolve these problems. In this paper, we formulate domain mismatch in face recognition as a style mismatch problem for which we propose two methods. First, we design a domain discriminator with human-level judgment to mine target-like images in the training data to mitigate the domain gap. Second, we extract style representations in low-level feature maps of the backbone model, and match the style distributions of the two domains to find a common style representation. Evaluations on verification and open-set and closed-set identification protocols show that both methods yield good improvements, and that performance is more robust if they are combined. Our approach is competitive with related work, and its effectiveness is verified in a practical application.

show abstract

Section: Domain Adaptation For Face Recognitionmentioning

confidence: 99%

Mitigating Domain Mismatch in Face Recognition Using Style Matching

Lin¹,

Wu²

2021

Preprint

View full text Add to dashboard Cite

show abstract

Prototype Memory for Large-Scale Face Representation Learning

Smirnov¹,

Garaev²,

Galyuk³

2022

IEEE Access

View full text Add to dashboard Cite

Face representation learning using datasets with a massive number of identities requires appropriate training methods. Softmax-based approach, currently the state-of-the-art in face recognition, in its usual "full softmax" form is not suitable for datasets with millions of persons. Several methods, based on the "sampled softmax" approach, were proposed to remove this limitation. These methods, however, have a set of disadvantages. One of them is a problem of "prototype obsolescence": classifier weights (prototypes) of the rarely sampled classes, receive too scarce gradients and become outdated and detached from the current encoder state, resulting in incorrect training signals. This problem is especially serious in ultra-large-scale datasets. In this paper, we propose a novel face representation learning model called Prototype Memory, which alleviates this problem and allows training on a dataset of any size. Prototype Memory consists of the limited-size memory module for storing recent class prototypes and employs a set of algorithms to update it in appropriate way. New class prototypes are generated on the fly using exemplar embeddings in the current mini-batch. These prototypes are enqueued to the memory and used in a role of classifier weights for softmax classification-based training. To prevent obsolescence and keep the memory in close connection with the encoder, prototypes are regularly refreshed, and oldest ones are dequeued and disposed of. Prototype Memory is computationally efficient and independent of dataset size. It can be used with various loss functions, hard example mining algorithms and encoder architectures. We prove the effectiveness of the proposed model by extensive experiments on popular face recognition benchmarks.

show abstract

Single Image Super-Resolution Reconstruction of Enhanced Loss Function with Multi-GPU Training

Huang

Wang

2019

2019 IEEE Intl Conf on Parallel &Amp; Distributed Processing With Applications, Big Data &Amp; Cloud Computing, Sustainable Com

View full text Add to dashboard Cite

Improve Cross-Domain Face Recognition with IBN-block

Cited by 4 publications

References 18 publications

Mitigating Domain Mismatch in Face Recognition Using Style Matching

Mitigating Domain Mismatch in Face Recognition Using Style Matching

Prototype Memory for Large-Scale Face Representation Learning

Single Image Super-Resolution Reconstruction of Enhanced Loss Function with Multi-GPU Training

Contact Info

Product

Resources

About