Disentangled Representation Learning GAN for Pose-Invariant Face Recognition

Tran, Luan; Yin, Xi; Liu, Xiaoming

doi:10.1109/cvpr.2017.141

Cited by 938 publications

(700 citation statements)

References 19 publications

Supporting

Mentioning

700

Contrasting

Order By: Relevance

“…Especially, GANs are known to be able to generate realistic samples, while the discriminator and the generator play a "two-player minimax game". Generating new type data using GANs and augementing with real data has been investigated in recent works (Baek, Kim, and Kim 2018;Gecer et al 2018;Zhang et al 2018;Shmelkov, Schmid, and Alahari 2018;Zhao et al 2018b;Tran, Yin, and Liu 2017;Zhao et al 2018a;Huang et al 2017) and too few to mention. In this paper, we try to investigate methods and tricks to sub-sample instead of randomly augmenting the synthetic images from GAN.…”

Section: Related Workmentioning

confidence: 99%

Sampling Strategies for GAN Synthetic Data

Bhattarai

Baek

Bodur

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Generative Adversarial Networks (GANs) have been used widely to generate large volumes of synthetic data. This data is being utilized for augmenting with real examples in order to train deep Convolutional Neural Networks (CNNs). Studies have shown that the generated examples lack sufficient realism to train deep CNNs and are poor in diversity. Unlike previous studies of randomly augmenting the synthetic data with real data, we present our simple, effective and easy to implement synthetic data sampling methods to train deep CNNs more efficiently and accurately. To this end, we propose to maximally utilize the parameters learned during training of the GAN itself. These include discriminator's realism confidence score and the confidence on the target label of the synthetic data. In addition to this, we explore reinforcement learning (RL) to automatically search a subset of meaningful synthetic examples from a large pool of GAN synthetic data. We evaluate our method on two challenging face attribute classification data sets viz. AffectNet and CelebA. Our extensive experiments clearly demonstrate the need of sampling synthetic data before augmentation, which also improves the performance of one of the state-of-the-art deep CNNs in vitro.

show abstract

Section: Related Workmentioning

confidence: 99%

Sampling Strategies for GAN Synthetic Data

Bhattarai

Baek

Bodur

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…Random noise is provided in the form of dropout. Compared with DR-GAN [24], we do not require the discriminator to explicitly recognize the character class of the generated glyph image, which is irrelevant in our case. To further encourage the generated image to have the same font style as the targeted one, we add an L 1 distance loss as [9]:…”

Section: Generative Feature Learningmentioning

confidence: 99%

Large-Scale Tag-Based Font Retrieval With Generative Feature Learning

Chen

Wang

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Font selection is one of the most important steps in a design workflow. Traditional methods rely on ordered lists which require significant domain knowledge and are often difficult to use even for trained professionals. In this paper, we address the problem of large-scale tag-based font retrieval which aims to bring semantics to the font selection process and enable people without expert knowledge to use fonts effectively. We collect a large-scale font tagging dataset of high-quality professional fonts. The dataset contains nearly 20,000 fonts, 2,000 tags, and hundreds of thousands of font-tag relations. We propose a novel generative feature learning algorithm that leverages the unique characteristics of fonts. The key idea is that font images are synthetic and can therefore be controlled by the learning algorithm. We design an integrated rendering and learning process so that the visual feature from one image can be used to reconstruct another image with different text. The resulting feature captures important font design details while is robust to nuisance factors such as text. We propose a novel attention mechanism to re-weight the visual feature for joint visual-text modeling. We combine the feature and the attention mechanism in a novel recognition-retrieval model. Experimental results show that our method significantly outperforms the state-of-the-art for the important problem of large-scale tag-based font retrieval.

show abstract

“…In recent years, deep learning has achieved outstanding performance in many computer vision tasks, including image classification [8], face recognition [9]. The great success of deep learning is mainly due to the powerful representation capability of deep neural networks and the available largescale labelled training data.…”

Section: Introductionmentioning

confidence: 99%

“…Through the adversarial optimization between these two networks, GAN is able to generate synthetic samples that simulate the distribution of real samples from training data. Particularly, GAN has been successfully used in some face-related tasks, such as posed face synthesis [9] and facial attributes transfer [18]. These methods are able to generate photo-realistic facial images having the same identity as the input facial images.…”

Section: Introductionmentioning

confidence: 99%

Joint Deep Learning of Facial Expression Synthesis and Recognition

Yan

Huang

Chen

et al. 2020

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Recently, deep learning based facial expression recognition (FER) methods have attracted considerable attention and they usually require large-scale labelled training data. Nonetheless, the publicly available facial expression databases typically contain a small amount of labelled data. In this paper, to overcome the above issue, we propose a novel joint deep learning of facial expression synthesis and recognition method for effective FER. More specifically, the proposed method involves a two-stage learning procedure. Firstly, a facial expression synthesis generative adversarial network (FESGAN) is pretrained to generate facial images with different facial expressions. To increase the diversity of the training images, FESGAN is elaborately designed to generate images with new identities from a prior distribution. Secondly, an expression recognition network is jointly learned with the pre-trained FESGAN in a unified framework. In particular, the classification loss computed from the recognition network is used to simultaneously optimize the performance of both the recognition network and the generator of FESGAN. Moreover, in order to alleviate the problem of data bias between the real images and the synthetic images, we propose an intra-class loss with a novel real data-guided back-propagation (RDBP) algorithm to reduce the intra-class variations of images from the same class, which can significantly improve the final performance. Extensive experimental results on public facial expression databases demonstrate the superiority of the proposed method compared with several state-of-the-art FER methods.Index Terms-Facial expression recognition, facial expression synthesis, convolutional neural networks (CNNs), generative adversarial net (GAN).

show abstract

Disentangled Representation Learning GAN for Pose-Invariant Face Recognition

Cited by 938 publications

References 19 publications

Sampling Strategies for GAN Synthetic Data

Sampling Strategies for GAN Synthetic Data

Large-Scale Tag-Based Font Retrieval With Generative Feature Learning

Joint Deep Learning of Facial Expression Synthesis and Recognition

Contact Info

Product

Resources

About