FCSR-GAN: Joint Face Completion and Super-Resolution via Multi-Task Learning

Cai, Jiancheng; Han, Hu; Shan, Shiguang; Chen, Xilin

doi:10.1109/tbiom.2019.2951063

Cited by 43 publications

(15 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, they proposed a feature-oriented blind face inpainting framework. Cai et al [11] proposed a method named FCSR-GAN to perform face completion and face super-resolution by multi-task learning where the generator was required to generate a highresolution face image without occlusion from the occluded low-resolution face image. Zhou et al [85] argued that previous works overlooked the serious impacts of inaccurate attention scores.…”

Section: Image Inpaintingmentioning

confidence: 99%

Contrastive Attention Network with Dense Field Estimation for Face Completion

Ma¹,

Zhou²,

Huang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Most modern face completion approaches adopt an autoencoder or its variants to restore missing regions in face images. Encoders are often utilized to learn powerful representations that play an important role in meeting the challenges of sophisticated learning tasks. Specifically, various kinds of masks are often presented in face images in the wild, forming complex patterns, especially in this hard period of COVID-19. It's difficult for encoders to capture such powerful representations under this complex situation. To address this challenge, we propose a self-supervised Siamese inference network to improve the generalization and robustness of encoders. It can encode contextual semantics from full-resolution images and obtain more discriminative representations. To deal with geometric variations of face images, a dense correspondence field is integrated into the network. We further propose a multi-scale decoder with a novel dual attention fusion module (DAF), which can combine the restored and known regions in an adaptive manner. This multi-scale architecture is beneficial for the decoder to utilize discriminative representations learned from encoders into images. Extensive experiments clearly demonstrate that the proposed approach not only achieves more appealing results compared with stateof-the-art methods but also improves the performance of masked face recognition dramatically.

show abstract

Section: Image Inpaintingmentioning

confidence: 99%

Contrastive Attention Network with Dense Field Estimation for Face Completion

Ma¹,

Zhou²,

Huang³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Comparison of SR and RI methods: The SR methods are intuitively appealing and a number of SR techniques, exhibiting a decent performance, are available in the literature [18], [19], [35], [36]. Since the SR techniques are primarily focused on creating visually appealing images, they are well suited for human-assisted face recognition tasks.…”

Section: A Face Recognitionmentioning

confidence: 99%

Resolution Invariant Face Recognition Using a Distillation Approach

Khalid

Awais

Feng

et al. 2020

IEEE Trans. Biom. Behav. Identity Sci.

View full text Add to dashboard Cite

Modern face recognition systems extract face representations using deep neural networks (DNNs) and give excellent identification and verification results, when tested on high resolution (HR) images. However, the performance of such an algorithm degrades significantly for low resolution (LR) images. A straight forward solution could be to train a DNN, using simultaneously, high and low resolution face images. This approach yields a definite improvement at lower resolutions but suffers a performance degradation for high resolution images. To overcome this shortcoming, we propose to train a network using both HR and LR images under the guidance of a fixed network, pretrained on HR face images. The guidance is provided by minimising the KL-divergence between the output Softmax probabilities of the pretrained (i.e., Teacher) and trainable (i.e., Student) network as well as by sharing the Softmax weights between the two networks. The resulting solution is tested on down-sampled images from FaceScrub and MegaFace datasets and shows a consistent performance improvement across various resolutions. We also tested our proposed solution on standard LR benchmarks such as TinyFace and SCFace. Our algorithm consistently outperforms the state-of-the-art methods on these datasets, confirming the effectiveness and merits of the proposed method.

show abstract

“…e concept of Chinese painting began to be widely used at the beginning of this century [1], and the concept was introduced as an affirmation of the ancient art of painting in China and as a way to preserve the national painting. Chinese painting has created a form of painting that belongs exclusively to China.…”

Section: Introductionmentioning

confidence: 99%

Application of Multitask Joint Sparse Representation Algorithm in Chinese Painting Image Classification

Yang

Ye²,

Guo

2021

Complexity

View full text Add to dashboard Cite

This paper presents an in-depth study and analysis of Chinese painting image classification by a multitask joint sparse representation algorithm for texture feature extraction of Chinese painting images and proposes a method to extract texture features directly for the original images. It simplifies the process of image grayscale conversion and preserves the information contained in the original Chinese painting images to the greatest extent. The algorithm uses the ideas of multicolor domain analysis and multiscale analysis, combined with the traditional grayscale coeval matrix to extract texture features. Experiments show that the multiscale grayscale cooccurrence matrix algorithm outperforms the traditional grayscale cooccurrence matrix algorithm and the color grayscale cooccurrence matrix algorithm. The discriminative ability of multiple features for target recognition is integrated by multitask learning, thus improving the robustness and generalization ability of the algorithm; meanwhile, the recognition accuracy is improved by using a two-level multitask learning mode to exclude the interference of a large number of irrelevant dictionary atoms. The experimental results show that the algorithm has higher recognition accuracy and better robustness than the existing sparse representation SAR target recognition algorithm. Configuration recognition experiments are conducted on different configurations of target data, and the experimental results show that the algorithm achieves better configuration recognition accuracy than existing algorithms.

show abstract

FCSR-GAN: Joint Face Completion and Super-Resolution via Multi-Task Learning

Cited by 43 publications

References 57 publications

Contrastive Attention Network with Dense Field Estimation for Face Completion

Contrastive Attention Network with Dense Field Estimation for Face Completion

Resolution Invariant Face Recognition Using a Distillation Approach

Application of Multitask Joint Sparse Representation Algorithm in Chinese Painting Image Classification

Contact Info

Product

Resources

About