FaceNet2ExpNet: Regularizing a Deep Face Recognition Net for Expression Recognition
Hui Ding,Shaohua Kevin Zhou,Rama Chellappa +2 more
- pp 118-126
Reads0
Chats0
TLDR
FaceNet2ExpNet as mentioned in this paper proposes a new distribution function to model the high-level neurons of the expression network, which achieves better results than state-of-the-art methods.Abstract:
Relatively small data sets available for expression recognition research make the training of deep networks very challenging. Although fine-tuning can partially alleviate the issue, the performance is still below acceptable levels as the deep features probably contain redundant information from the pretrained domain. In this paper, we present FaceNet2ExpNet, a novel idea to train an expression recognition network based on static images. We first propose a new distribution function to model the high-level neurons of the expression network. Based on this, a two-stage training algorithm is carefully designed. In the pre-training stage, we train the convolutional layers of the expression net, regularized by the face net; In the refining stage, we append fully-connected layers to the pre-trained convolutional layers and train the whole network jointly. Visualization results show that the model trained with our method captures improved high-level expression semantics. Evaluations on four public expression databases, CK+, Oulu- CASIA, TFD, and SFEW demonstrate that our method achieves better results than state-of-the-art.read more
Citations
More filters
Proceedings ArticleDOI
Weakly-Supervised Deep Convolutional Neural Network Learning for Facial Action Unit Intensity Estimation
TL;DR: This work proposes a novel knowledge-based semi-supervised deep convolutional neural network for AU intensity estimation with extremely limited AU annotations, which can achieve comparable or even better performance than the state-of-the-art methods.
Posted Content
Identity-Free Facial Expression Recognition using conditional Generative Adversarial Network
TL;DR: Experiments on four facial expression datasets show that IF-GAN outperforms the baseline CNN and achieves state-of-the-art performance for FER.
Journal ArticleDOI
Facial Expressions Recognition for Human-Robot Interaction Using Deep Convolutional Neural Networks with Rectified Adam Optimizer.
TL;DR: The interaction between humans and an NAO robot using deep convolutional neural networks (CNN) is presented in this paper based on an innovative end-to-end pipeline method that applies two optimized CNNs, one for face recognition (FR) and another one for the facial expression recognition (FER) in order to obtain real-time inference speed for the entire process.
Journal ArticleDOI
Extracting human emotions at different places based on facial expressions and spatial clustering analysis
Yuhao Kang,Yuhao Kang,Qingyuan Jia,Song Gao,Xiaohuan Zeng,Yueyao Wang,Yueyao Wang,Stephan Angsuesser,Yu Liu,Xinyue Ye,Teng Fei +10 more
TL;DR: A novel framework for extracting human emotions from large‐scale georeferenced photos at different places is proposed and a happiness ranking list of places is generated based on human emotions calculated over 2 million faces detected from greater than 6 million photos.
Journal ArticleDOI
Facial expression recognition boosted by soft label with a diverse ensemble
TL;DR: A novel FER framework using a CNN and soft label that associates multiple emotions with each expression is presented and a novel label-level perturbation strategy to train multiple base classifiers with diversity is proposed.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Journal Article
Dropout: a simple way to prevent neural networks from overfitting
TL;DR: It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.
Proceedings ArticleDOI
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TL;DR: RCNN as discussed by the authors combines CNNs with bottom-up region proposals to localize and segment objects, and when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost.