ABSTRACT
The deep learning algorithm called convolutional neural network (CNN) particularly with Residual Network (ResNet) receiving much attention from the research community in facial recognition recently. Unfortunately, the complexity of optimization problems in overfitting and vanishing gradient cause huge obstacles. More specifically, once the gradient is backpropagated in initial layers, repeated multiplication among layers constructs gradient infinitely small and causes the layers of the network to become deeper and degrade the performance. Moreover, the skip connection that comprises the residual network (ResNet) is not enough to solve the above-mentioned limitations, and this could downgrade the optimization of used layers and potentially further downgrade the accuracy. Therefore, a deep residual network (ResNet) with hybridized function i.e., convolutional-2D and Batch Norm is proposed as this could allow direct signal propagation from the initial to the final layer of the network for every single residual block deeply. Initially, the convolutional-2D and Batch Norm were constructed to overcome bias in-depth nets and propagate the gradients directly from the loss layers to any previous layers, while skipping intermediate weight layers deeply that have the potential to trigger vanishing or deterioration of the gradient signal. The proposed learning model has improved the degradation of accuracy drawback by decreasing the number of layers needed more in low level as compared to existing work for each block using batch normalization and convolutional-2D function.
Supplemental Material
Available for Download
Presentation slides
- Amirali Abdolrashidi, Mehdi Minaei, Elham Azimi, and Shervin Minaee. 2020. Age and Gender Prediction From Face Images Using Attentional Convolutional Network. (October 2020). Retrieved from http://arxiv.org/abs/2010.03791Google Scholar
- B. Abirami, T.S. Subashini, and V. Mahavaishnavi. 2020. Gender and age prediction from real time facial images using CNN. Mater. Today Proc. 33, (2020), 4708–4712. DOI:https://doi.org/10.1016/j.matpr.2020.08.350Google Scholar
- P Aiswarya, Manish, and P. Mangalraj. 2020. Emotion recognition by inclusion of age and gender parameters with a novel hierarchical approach using deep learning. In 2020 Advanced Communication Technologies and Signal Processing (ACTS), IEEE, 1–6. DOI:https://doi.org/10.1109/ACTS49415.2020.9350479Google Scholar
- Md Zahangir Alom, Tarek M. Taha, Chris Yakopcic, Stefan Westberg, Paheding Sidike, Mst Shamima Nasrin, Mahmudul Hasan, Brian C. Van Essen, Abdul A. S. Awwal, and Vijayan K. Asari. 2019. A State-of-the-Art Survey on Deep Learning Theory and Architectures. Electronics 8, 3 (March 2019), 292. DOI:https://doi.org/10.3390/electronics8030292Google ScholarCross Ref
- Myungsu Chae, Tae-Ho Kim, Young Hoon Shin, June-Woo Kim, and Soo-Young Lee. 2018. End-to-end Multimodal Emotion and Gender Recognition with Dynamic Joint Loss Weights. (September 2018). Retrieved from http://arxiv.org/abs/1809.00758Google Scholar
- Wei-Lun Chao, Jun-Zuo Liu, and Jian-Jiun Ding. 2013. Facial age estimation based on label-sensitive learning and age-oriented regression. Pattern Recognit. 46, 3 (March 2013), 628–641. DOI:https://doi.org/10.1016/j.patcog.2012.09.011Google ScholarDigital Library
- G. E. Dahl, Dong Yu, Li Deng, and A. Acero. 2012. Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition. IEEE Trans. Audio. Speech. Lang. Processing 20, 1 (January 2012), 30–42. DOI:https://doi.org/10.1109/TASL.2011.2134090Google ScholarDigital Library
- Abhijit Das, Antitza Dantcheva, and Francois Bremond. 2018. Mitigating Bias in Gender, Age and Ethnicity Classification: a Multi-Task Convolution Neural Network Approach. In ECCVW 2018 - European Conference of Computer Vision Workshops, Munich, Germany. Retrieved from https://hal.inria.fr/hal-01892103Google ScholarDigital Library
- Poonam Dhankhar and New Delhi. 2019. ResNet-50 and VGG-16 for recognizing Facial Emotions. Int. J. Innov. Eng. Technol. 13, 4 (2019), 126–130.Google Scholar
- Amit Dhomne, Ranjit Kumar, and Vijay Bhan. 2018. Gender Recognition Through Face Using Deep Learning. Procedia Comput. Sci. 132, (2018), 2–10. DOI:https://doi.org/10.1016/j.procs.2018.05.053Google ScholarDigital Library
- Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning. MIT Press.Google ScholarDigital Library
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Deep Residual Learning for Image Recognition. (December 2015). Retrieved from http://arxiv.org/abs/1512.03385Google Scholar
- D. H. Hubel and T. N. Wiesel. 1962. Receptive fields, binocular interaction and functional architecture in the cat's visual cortex. J. Physiol. 160, 1 (January 1962), 106–154. DOI:https://doi.org/10.1113/jphysiol.1962.sp006837Google ScholarCross Ref
- Shaik Asif Hussain and Ahlam Salim Abdallah Al Balushi. 2020. A real time face emotion classification and recognition using deep learning model. J. Phys. Conf. Ser. 1432, (January 2020), 12087. DOI:https://doi.org/10.1088/1742-6596/1432/1/012087Google Scholar
- Koichi Ito, Hiroya Kawai, Takehisa Okano, and Takafumi Aoki. 2018. Age and Gender Prediction from Face Images Using Convolutional Neural Network. In 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), IEEE, 7–11. DOI:https://doi.org/10.23919/APSIPA.2018.8659655Google ScholarCross Ref
- Amany Kandeel, Mina Rahmanian, Farhana Zulkernine, Hazem M. Abbas, and Hossam Hassanein. 2021. Facial Expression Recognition Using a Simplified Convolutional Neural Network Model. In 2020 International Conference on Communications, Signal Processing, and their Applications (ICCSPA), IEEE, 1–6. DOI:https://doi.org/10.1109/ICCSPA49915.2021.9385739Google ScholarCross Ref
- Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2017. ImageNet classification with deep convolutional neural networks. Commun. ACM 60, 6 (May 2017), 84–90. DOI:https://doi.org/10.1145/3065386Google ScholarDigital Library
- Hrishikesh Kulkarni and Ghassem Tofighi. 2018. Unconstrained Facial Recognition using Supervised Deep Learning on Video. May (2018), 1–8.Google Scholar
- Seok Hee Lee, Sepidehsadat Hosseini, Hyuk Jin Kwon, Jaewon Moon, Hyung Il Koo, and Nam Ik Cho. 2018. Age and gender estimation using deep residual learning network. In 2018 International Workshop on Advanced Image Technology (IWAIT), IEEE, 1–3. DOI:https://doi.org/10.1109/IWAIT.2018.8369763Google ScholarCross Ref
- Gil Levi and Tal Hassncer. 2015. Age and gender classification using convolutional neural networks. In 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), IEEE, 34–42. DOI:https://doi.org/10.1109/CVPRW.2015.7301352Google ScholarCross Ref
- Shervin Minaee and Amirali Abdolrashidi. 2019. Deep-Emotion: Facial Expression Recognition Using Attentional Convolutional Network. (February 2019). Retrieved from http://arxiv.org/abs/1902.01019Google Scholar
- Sebastian W Ober, Carl E Rasmussen, and Mark van der Wilk. 2021. The Promises and Pitfalls of Deep Kernel Learning.Google Scholar
- Zakariya Qawaqneh, Arafat Abu Mallouh, and Buket D. Barkana. 2017. Deep Convolutional Neural Network for Age Estimation based on VGG-Face Model. (September 2017). Retrieved from http://arxiv.org/abs/1709.01664Google Scholar
- Andrew Jason Shepley. 2019. Deep Learning For Face Recognition: A Critical Analysis. (July 2019). Retrieved from http://arxiv.org/abs/1907.12739Google Scholar
- Karen Simonyan and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. (September 2014). Retrieved from http://arxiv.org/abs/1409.1556Google Scholar
- Philip Smith and Cuixian Chen. 2018. Transfer Learning with Deep CNNs for Gender Recognition and Age Estimation. (November 2018). Retrieved from http://arxiv.org/abs/1811.07344Google Scholar
- Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. 2014. Going Deeper with Convolutions. (September 2014). Retrieved from http://arxiv.org/abs/1409.4842Google Scholar
- Chintan Thackher. 2019. Human Behavior Analysis through Facial Expression Recognition in Images using Deep Learning. Int. J. Innov. Technol. Explor. Eng. 9, 2 (December 2019), 391–397. DOI:https://doi.org/10.35940/ijitee.B6379.129219Google Scholar
- Kai-Yuan Tsai, Yi-Wei Tsai, Yih-Cherng Lee, Jian-Jiun Ding, and Ronald Y. Chang. 2021. Frontalization and adaptive exponential ensemble rule for deep-learning-based facial expression recognition system. Signal Process. Image Commun. 96, (August 2021), 116321. DOI:https://doi.org/10.1016/j.image.2021.116321Google Scholar
- Muhammad Umair and Muhammad Naqeeb Nazir. 2021. Classification of Demographic Attributes from Facial Image by using CNN. In 2021 International Conference on Artificial Intelligence (ICAI), IEEE, 68–73. DOI:https://doi.org/10.1109/ICAI52203.2021.9445248Google ScholarCross Ref
- Shuo Yang, Ping Luo, Chen Change Loy, and Xiaoou Tang. 2017. Faceness-Net: Face Detection through Deep Facial Part Responses. (January 2017). Retrieved from http://arxiv.org/abs/1701.08393Google Scholar
- Matthew D. Zeiler and Rob Fergus. 2014. Visualizing and Understanding Convolutional Networks. . 818–833. DOI:https://doi.org/10.1007/978-3-319-10590-1_53Google Scholar
- Zhiwei Zhao and Youzheng Wu. 2016. Attention-Based Convolutional Neural Networks for Sentence Classification. 705–709. DOI:https://doi.org/10.21437/Interspeech.2016-354Google Scholar
Recommendations
Residual Learning for FC Kernels of Convolutional Network
Artificial Neural Networks and Machine Learning – ICANN 2019: Deep LearningAbstractOne of the most important steps in training a neural network is choosing its depth. Theoretically, it is possible to construct a complex decision-making function by cascading a number of shallow networks. It can produce a similar in accuracy ...
Improved inception-residual convolutional neural network for object recognition
AbstractMachine learning and computer vision have driven many of the greatest advances in the modeling of Deep Convolutional Neural Networks (DCNNs). Nowadays, most of the research has been focused on improving recognition accuracy with better DCNN models ...
Network anomaly detection using channel boosted and residual learning based deep convolutional neural network
AbstractAnomaly detection in a network is one of the prime concerns for network security. In this work, a novel Channel Boosted and Residual learning based deep Convolutional Neural Network (CBR-CNN) architecture is proposed for the detection ...
Graphical abstractDisplay Omitted
Highlights- An effective network intrusion detection system is developed using one-class classification.
Comments