Improved softmax loss for deep learning‐based face and expression recognition

Zhou, Jiancan; Jia, Xibin; Shen, Linlin; Wen, Zhenkun; Zhong, Ming

doi:10.1049/ccs.2019.0010

Cited by 14 publications

(10 citation statements)

References 20 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the advent of deep learning, end-to-end feature extraction through CNN is being practised widely in miscellaneous applications. Zhou et al adopted deep CNN architecture with improved softmax loss for face and expression recognition [36]. In [37], Basnet et al estimated instantaneous emotional states from facial video using audiovisual features extracted from CNNs.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of instantaneous likeability of advertisements using deep learning

Saha

Rahman

Islam

et al. 2021

Cognitive Comp and Systems

View full text Add to dashboard Cite

The degree to which advertisements are successful is of prime concern for vendors in highly competitive global markets. Given the astounding growth of multimedia content on the internet, online marketing has become another form of advertising. Researchers consider advertisement likeability a major predictor of effective market penetration. An algorithm is presented to predict how much an advertisement clip will be liked with the aid of an end-to-end audiovisual feature extraction process using cognitive computing technology. Specifically, the usefulness of different spatial and time-domain deeplearning architectures such as convolutional neural and long short-term memory networks is investigated to predict the frame-by-frame instantaneous and root mean square likeability of advertisement clips. A data set named the 'BUET Advertisement Likeness Data Set', containing annotations of frame-wise likeability scores for various categories of advertisements, is also introduced. Experiments with the developed database show that the proposed algorithm performs better than existing methods in terms of commonly used performance indices at the expense of slightly increased computational complexity.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: Related Workmentioning

confidence: 99%

“…Zhou et al. adopted deep CNN architecture with improved softmax loss for face and expression recognition [36]. In [37], Basnet et al.…”

Section: Introductionmentioning

confidence: 99%

Prediction of instantaneous likeability of advertisements using deep learning

Saha

Rahman

Islam

et al. 2021

Cognitive Comp and Systems

View full text Add to dashboard Cite

show abstract

“…In the process of training the model, the model extracts image features and predicts the category of the image. What the loss function does is to compare the model prediction with the ground truth of each image, and then calculate the gap between them [8]. If the model prediction and ground truth are of the same category, then we hope that the gap between them should be as small as possible, or even 0; if the model prediction and ground truth are of different categories, then we hope that the gap between them should be as great as possible, even infinite.…”

Section: Preliminary Workmentioning

confidence: 99%

Error Refactor loss based on error analysis in image classification

Chen

Zhou

et al. 2021

IET Computer Vision

View full text Add to dashboard Cite

The loss function is a criterion to evaluate the learning quality of a deep convolutional neural network, which represents the gap between prediction and ground truth. However, as the most commonly used loss function in image classification tasks, Cross-Entropy loss does not encourage the model to distinguish the similarity between features. In this work, the authors investigate inter-class separability of similar features learnt by convolutional networks and propose a loss function called Error Refactor Loss (ER-Loss). ER-Loss is based on the error caused by convolutional networks; it can improve the inter-class separability and is simple to implement and can easily replace the Cross-Entropy loss. Compared with softmax loss, ER-Loss adds a dynamic penalty item which can help ER-Loss monitor the actual situation of model training and adjust the value of the penalty item according to model training. The ER-Loss on CIFAR100 and part of ImageNet ILSVRC 2012 is evaluated and the experimental result showed that the ER-Loss can improve the accuracy of the model.

show abstract

“…With the boom of deep learning, its ideas gradually seep into all walks of life, such as face and expression identification [7], daily activities monitoring [8][9][10], target tracking [11]. In the field of marine life exploration, many scholars have also applied this idea to automatic fish classification [12] and catfish density estimation [13].…”

Section: Introductionmentioning

confidence: 99%

Deep learning techniques‐based perfection of multi‐sensor fusion oriented human‐robot interaction system for identification of dense organisms

Hai-ju

Zhang

et al. 2021

Cognitive Comp and Systems

View full text Add to dashboard Cite

For detection of dense small-target organisms with indistinct features in complex background, the efficiency and accuracy of traditional target detection methods are low. Multi-sensor fusion oriented human-robot interaction (HRI) system has facilitated biologists to process and analyse data. For this, several deep learning models based on convolutional neural network (CNN) are improved and compared to study the species and density of dense organisms in deep-sea hydrothermal vent, which are fused it with related environmental information given by position sensors and conductivity-temperature-depth (CTD) sensors, so as to perfect multi-sensor fusion oriented HRI system. Firstly, the authors combined different meta-architectures and different feature extractors, and obtained five object identification algorithms based on CNN. Then, they compared computational cost of feature extractors and weighed the pros and cons of each algorithm from mean detection speed, correlation coefficient and mean class-specific confidence score to confirm that Faster Region-based CNN (R-CNN)_InceptionNet is the best algorithm applicable to hydrothermal vent biological dataset. Finally, they calculated the cognitive accuracy of rimicaris exoculata in dense and sparse areas, which were 88.3% and 95.9% respectively, to analyse the performance of the Faster R-CNN_InceptionNet. Results show that the proposed method can be used in the multi-sensor fusion oriented HRI system for the statistics of dense organisms in complex environments.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

Improved softmax loss for deep learning‐based face and expression recognition

Cited by 14 publications

References 20 publications

Prediction of instantaneous likeability of advertisements using deep learning

Prediction of instantaneous likeability of advertisements using deep learning

Error Refactor loss based on error analysis in image classification

Deep learning techniques‐based perfection of multi‐sensor fusion oriented human‐robot interaction system for identification of dense organisms

Contact Info

Product

Resources

About