R³ Adversarial Network for Cross Model Face Recognition

Chen, Ken; Wu, Yichao; Qin, Haoyu; Ding, Liang; Liu, Xuebo; Yan, Junjie

doi:10.1109/cvpr.2019.01010

Cited by 32 publications

(29 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GANs are utilized in solving general face recognition problems as cross-age face recognition, face synthesis, poseinvariant face recognition, video-based face recognition, makeup-invariant face recognition, and so on. For example, R3AN architecture [85] was proposed for cross model FR problem. It divides the method into three paths: reconstruction, representation, and regression for training.…”

Section: Generative Adversarial Networkmentioning

confidence: 99%

Recent Advances in Deep Learning Techniques for Face Recognition

et al. 2021

View full text Add to dashboard Cite

In recent years, researchers have proposed many deep learning (DL) methods for various tasks, and particularly face recognition (FR) made an enormous leap using these techniques. Deep FR systems benefit from the hierarchical architecture of the DL methods to learn discriminative face representation. Therefore, DL techniques significantly improve state-of-the-art performance on FR systems and encourage diverse and efficient real-world applications. In this paper, we present a comprehensive analysis of various FR systems that leverage the different types of DL techniques, and for the study, we summarize 171 recent contributions from this area. We discuss the papers related to different algorithms, architectures, loss functions, activation functions, datasets, challenges, improvement ideas, current and future trends of DL-based FR systems. We provide a detailed discussion of various DL methods to understand the current state-of-the-art, and then we discuss various activation and loss functions for the methods. Additionally, we summarize different datasets used widely for FR tasks and discuss challenges related to illumination, expression, pose variations, and occlusion. Finally, we discuss improvement ideas, current and future trends of FR tasks. INDEX TERMSDeep learning, face recognition, artificial neural network, convolutional neural network, auto encoder, generative adversarial network, deep belief network, reinforcement learning.

show abstract

Section: Generative Adversarial Networkmentioning

confidence: 99%

Recent Advances in Deep Learning Techniques for Face Recognition

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Cross-model compatibility: The broad goal of this area is to ensure embeddings generated by different models are compatible. Some recent works ensure cross-model compatibility by learning transformation functions from the query embedding space to the gallery one [33,5,13]. Different from these works, our approach directly optimizes the query model such that its metric space aligns with that of the gallery.…”

Section: Related Workmentioning

confidence: 99%

Compatibility-aware Heterogeneous Visual Search

Duggal¹,

Zhang²,

Yang³

et al. 2021

Preprint

View full text Add to dashboard Cite

We tackle the problem of visual search under resource constraints. Existing systems use the same embedding model to compute representations (embeddings) for the query and gallery images. Such systems inherently face a hard accuracy-efficiency trade-off: the embedding model needs to be large enough to ensure high accuracy, yet small enough to enable query-embedding computation on resource-constrained platforms. This trade-off could be mitigated if gallery embeddings are generated from a large model and query embeddings are extracted using a compact model. The key to building such a system is to ensure representation compatibility between the query and gallery models. In this paper, we address two forms of compatibility: One enforced by modifying the parameters of each model that computes the embeddings. The other by modifying the architectures that compute the embeddings, leading to compatibility-aware neural architecture search (CMP-NAS). We test CMP-NAS on challenging retrieval tasks for fashion images (DeepFashion2), and face images (IJB-C). Compared to ordinary (homogeneous) visual search using the largest embedding model (paragon), CMP-NAS achieves 80-fold and 23-fold cost reduction while maintaining accuracy within 0.3% and 1.6% of the paragon on DeepFashion2 and IJB-C respectively.

show abstract

“…They present BCT, an algorithm that allows new embedding models to be compatible with old models through a joint training procedure involving a distillation loss. Other works [8,29,46] attempt to construct a unified representation space on which models are compatible. These procedures also modify training of individual models to ensure that they are easy to transform to this unified embedding space.…”

Section: Related Workmentioning

confidence: 99%

Forward Compatible Training for Large-Scale Embedding Retrieval Systems

Ramanujan¹,

Vasu²,

Farhadi³

et al. 2021

Preprint

View full text Add to dashboard Cite

In visual retrieval systems, updating the embedding model requires recomputing features for every piece of data. This expensive process is referred to as backfilling. Recently, the idea of backward compatible training (BCT) was proposed. To avoid the cost of backfilling, BCT modifies training of the new model to make its representations compatible with those of the old model. However, BCT can significantly hinder the performance of the new model. In this work, we propose a new learning paradigm for representation learning: forward compatible training (FCT). In FCT, when the old model is trained, we also prepare for a future unknown version of the model. We propose learning sideinformation, an auxiliary feature for each sample which facilitates future updates of the model. To develop a powerful and flexible framework for model compatibility, we combine side-information with a forward transformation from old to new embeddings. Training of the new model is not modified, hence, its accuracy is not degraded. We demonstrate significant retrieval accuracy improvement compared to BCT for various datasets: ImageNet-1k (+18.1%), Places-365 (+5.4%), and VGG-Face2 (+8.3%). FCT obtains model compatibility when the new and old models are trained across different datasets, losses, and architectures.

show abstract

R³ Adversarial Network for Cross Model Face Recognition

Cited by 32 publications

References 16 publications

Recent Advances in Deep Learning Techniques for Face Recognition

Recent Advances in Deep Learning Techniques for Face Recognition

Compatibility-aware Heterogeneous Visual Search

Forward Compatible Training for Large-Scale Embedding Retrieval Systems

Contact Info

Product

Resources

About