Face Representation Learning using Composite Mini-Batches

Smirnov, Evgeny; Oleinik, Andrei; Aleksandr, Lavrentev; Shulga, Elizaveta; Galyuk, Vasiliy; Garaev, Nikita; Zakuanova, Margarita; Melnikov, Aleksandr

doi:10.1109/iccvw.2019.00068

Cited by 6 publications

(8 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, Prototype Memory introduces the operation of prototype generation, which also uses some extra computation, but is independent of the number of classes and much faster. For the case of usual training, we used composite minibatch [56], containing 128 images, sampled with "groupbased iterate-and-shuffle" strategy, and 384 images, sampled with "group-based classes-then-images" strategy. We also used m = 0.5 as margin value in CosFace.…”

Section: Methodsmentioning

confidence: 99%

“…There are also many complementary methods proposed to build better face recognition models by promoting desired properties of the produced face representations, such as robustness to noisy labels [8] and low image resolution [50], invariance to age [51] and pose [52], ability to mitigate racial bias [53] and domain imbalance [35], [54], to improve the fairness of representations [55]. There are also methods, proposed to overcome the problems with the situations of difficult face appearance variations, like deliberately disguised faces [31], [56] or faces in medical masks [57].…”

Section: Related Work a Face Recognitionmentioning

confidence: 99%

“…These methods could be combined with algorithms of hard class mining [30] and hard example mining [31], or used together as parts of a composite mini-batch [56].…”

Section: Solution To Prototype Obsolescencementioning

confidence: 99%

See 2 more Smart Citations

Prototype Memory for Large-Scale Face Representation Learning

Smirnov¹,

Garaev²,

Galyuk³

2022

IEEE Access

Self Cite

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

Section: Methodsmentioning

confidence: 99%

Section: Related Work a Face Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

Prototype Memory for Large-Scale Face Representation Learning

Smirnov¹,

Garaev²,

Galyuk³

2022

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…There are also many complementary methods proposed to build better face recognition models by promoting desired properties of the produced face representations, such as robustness to noisy labels [8] and low image resolution [50], invariance to age [51] and pose [52], ability to mitigate racial bias [53] and domain imbalance [35], [54], to improve the fairness of representations [115]. There are also methods, proposed to overcome the problems with the situations of difficult face appearance variations, like deliberately disguised faces [31], [55] or faces in medical masks [56].…”

Section: Related Work a Face Recognitionmentioning

confidence: 99%

“…These methods could be combined with algorithms of hard class mining [30] and hard example mining [31], or used together as parts of a composite mini-batch [55].…”

Section: Solution To Prototype Obsolescencementioning

confidence: 99%

Prototype Memory for Large-scale Face Representation Learning

Smirnov,

Garaev,

Galyuk

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Face representation learning using datasets with 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 an 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 usual softmax classification-based training. To prevent obsolescence and keep the memory in close connection with encoder, prototypes are regularly refreshed, and oldest ones are dequeued and disposed. 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