Rotating your face using multi-task deep neural network

Yim, Junho; Jung, Heechul; Yoo, Byueng–Su; Choi, Changkyu; Park, Du‐Sik; Kim, Junmo

doi:10.1109/cvpr.2015.7298667

Cited by 89 publications

(24 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Datasets Here, we train our model on the Multi-PIE [17] dataset To compare the results of the proposed method with those of the state-of-the-art methods, we also conduct experiments on Multi-PIE Setting-1 [19,21,25,32], which contains images of 250 identities in session one. The first 150 identities are used for training and the remaining 100 identities are used for testing.…”

Section: Datasets and Implementation Detailsmentioning

confidence: 99%

Multi‐factor joint normalisation for face recognition in the wild

Liu

Chen

2021

IET Computer Vision

View full text Add to dashboard Cite

Face recognition has become very challenging in unconstrained conditions due to strong intra-personal variations, such as large pose changes. Face normalisation can help to resolve these problems and effectively improve the face recognition performance in unconstrained conditions by converting non-frontal faces to frontal ones. However, there are other complex facial variations in addition to pose, such as illumination and expression, which will also influence face recognition performance. The authors propose a well-designed generative adversarial network-based multi-factor joint normalisation network (MFJNN) to normalise multiple factors simultaneously. First, a multi-encoder generator and a feature fusion strategy are designed and implemented in the MFJNN to realise the joint normalisation of multiple factors in addition to pose. Second, a convolutional neural networkbased (CNN-based) network is applied in the MFJNN, which allows the MFJNN to simultaneously realise image synthesis and facial representation learning. Moreover, an identity perceptive loss is introduced based on the CNN-based network to produce reliable identity-preserving features of the input face images. The experimental results demonstrate that the proposed method can synthesise multi-factor normalisation results with identity preservation and effectively improve the face recognition performance.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Section: Datasets and Implementation Detailsmentioning

confidence: 99%

Multi‐factor joint normalisation for face recognition in the wild

Liu

Chen

2021

IET Computer Vision

View full text Add to dashboard Cite

show abstract

“…Multi-task learning has been widely studied in deep learning, which leverages the information among different tasks to improve the generalization performance [3,6,28]. Fares et al [7] empirically evaluated the utility of transfer and multi-task learning on semantic interpretation of noun-noun compounds.…”

Section: Multi-task Learningmentioning

confidence: 99%

Model Compression with Two-stage Multi-teacher Knowledge Distillation for Web Question Answering System

Yang

Shou

Gong

et al. 2020

Proceedings of the 13th International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

Deep pre-training and fine-tuning models (such as BERT and Ope-nAI GPT) have demonstrated excellent results in question answering areas. However, due to the sheer amount of model parameters, the inference speed of these models is very slow. How to apply these complex models to real business scenarios becomes a challenging but practical problem. Previous model compression methods usually suffer from information loss during the model compression procedure, leading to inferior models compared with the original one. To tackle this challenge, we propose a Two-stage Multi-teacher Knowledge Distillation (TMKD for short) method for web Question Answering system. We first develop a general Q&A distillation task for student model pre-training, and further fine-tune this pretrained student model with multi-teacher knowledge distillation on downstream tasks (like Web Q&A task, MNLI, SNLI, RTE tasks from GLUE), which effectively reduces the overfitting bias in individual teacher models, and transfers more general knowledge to the student model. The experiment results show that our method can significantly outperform the baseline methods and even achieve comparable results with the original teacher models, along with substantial speedup of model inference.

show abstract

“…The result shows that their method could dealing with faces with head pose variation and severe occlusion. Junho Yim et al [27] used multi task deep learning to rotate human face. The main task could rotate the face to a custom angle and the additional task rotate the face to 30 degrees.…”

Section: Fig 2 Examples Of Facial Action Unitmentioning

confidence: 99%

Facial Action Unit Detection with Multilayer Fused Multi-Task and Multi-Label Deep Learning Network

2019

KSII TIIS

View full text Add to dashboard Cite

Facial action units (AUs) have recently drawn increased attention because they can be used to recognize facial expressions. A variety of methods have been designed for frontal-view AU detection, but few have been able to handle multi-view face images. In this paper we propose a method for multi-view facial AU detection using a fused multilayer, multi-task, and multi-label deep learning network. The network can complete two tasks: AU detection and facial view detection. AU detection is a multi-label problem and facial view detection is a single-label problem. A residual network and multilayer fusion are applied to obtain more representative features. Our method is effective and performs well. The F1 score on FERA 2017 is 13.1% higher than the baseline. The facial view recognition accuracy is 0.991. This shows that our multi-task, multi-label model could achieve good performance on the two tasks.

show abstract

Rotating your face using multi-task deep neural network

Cited by 89 publications

References 20 publications

Multi‐factor joint normalisation for face recognition in the wild

Multi‐factor joint normalisation for face recognition in the wild

Model Compression with Two-stage Multi-teacher Knowledge Distillation for Web Question Answering System

Facial Action Unit Detection with Multilayer Fused Multi-Task and Multi-Label Deep Learning Network

Contact Info

Product

Resources

About