A Cascaded Feature Pyramid Network With Non-Backward Propagation for Facial Expression Recognition

Yang, Wei; Gao, Hongwei; Jiang, Yueqiu; Yu, Jiahui; Sun, Jian; Liu, Jinguo; Ju, Zhaojie

doi:10.1109/jsen.2020.2997182

Cited by 13 publications

(5 citation statements)

References 30 publications

(29 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are a few earlier works concerning the use of feature pyramid in facial expression recognition [41] [37]. However, they only focus on a single task and we show that the feature pyramid also works for multi-task affective analysis.…”

Section: Multi-task Feature Pyramid Networkmentioning

confidence: 74%

Feature Pyramid Network for Multi-task Affective Analysis

He,

Xing,

Tan

et al. 2021

Preprint

View full text Add to dashboard Cite

Affective Analysis is not a single task, and the valencearousal value, expression class, and action unit can be predicted at the same time. Previous researches did not pay enough attention to the entanglement and hierarchical relation of these three facial attributes. We propose a novel model named feature pyramid networks for multi-task affect analysis. The hierarchical features are extracted to predict three labels and we apply a teacher-student training strategy to learn from pretrained single-task models. Extensive experiment results demonstrate the proposed model outperforms other models. This is a submission to The 2nd Workshop and Competition on Affective Behavior Analysis in the wild (ABAW). The code and model are available for research purposes at this link.

show abstract

Section: Multi-task Feature Pyramid Networkmentioning

confidence: 74%

Feature Pyramid Network for Multi-task Affective Analysis

He,

Xing,

Tan

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Deep learning (DL) algorithms are extensively implemented in multiple fields and have achieved incredible results, such as facial expression recognition and human pose estimation [5,6]. The state-of-the-art dehazing algorithm is wholly based on data-driven learning [7], including the haze-free image generation method based on CNNs and ViTs.…”

Section: Related Workmentioning

confidence: 99%

A Novel Approach to Maritime Image Dehazing Based on a Large Kernel Encoder–Decoder Network with Multihead Pyramids

et al. 2022

Self Cite

View full text Add to dashboard Cite

With the continuous increase in human–robot integration, battlefield formation is experiencing a revolutionary change. Unmanned aerial vehicles, unmanned surface vessels, combat robots, and other new intelligent weapons and equipment will play an essential role on future battlefields by performing various tasks, including situational reconnaissance, monitoring, attack, and communication relay. Real-time monitoring of maritime scenes is the basis of battle-situation and threat estimation in naval battlegrounds. However, images of maritime scenes are usually accompanied by haze, clouds, and other disturbances, which blur the images and diminish the validity of their contents. This will have a severe adverse impact on many downstream tasks. A novel large kernel encoder–decoder network with multihead pyramids (LKEDN-MHP) is proposed to address some maritime image dehazing-related issues. The LKEDN-MHP adopts a multihead pyramid approach to form a hybrid representation space comprising reflection, shading, and semanteme. Unlike standard convolutional neural networks (CNNs), the LKEDN-MHP uses many kernels with a 7 × 7 or larger scale to extract features. To reduce the computational burden, depthwise (DW) convolution combined with re-parameterization is adopted to form a hybrid model stacked by a large number of different receptive fields, further enhancing the hybrid receptive fields. To restore the natural hazy maritime scenes as much as possible, we apply digital twin technology to build a simulation system in virtual space. The final experimental results based on the evaluation metrics of the peak signal-to-noise ratio, structural similarity index measure, Jaccard index, and Dice coefficient show that our LKEDN-MHP significantly enhances dehazing and real-time performance compared with those of state-of-the-art approaches based on vision transformers (ViTs) and generative adversarial networks (GANs).

show abstract

“…This ANN can ignore this issue. Recently this ANN model has been used in the computer vision research area for recognizing facial expression [158].…”

Section: B Advantages Of Hsic Bottleneckmentioning

confidence: 99%

HSIC Bottleneck Based Distributed Deep Learning Model for Load Forecasting in Smart Grid With a Comprehensive Survey

et al. 2020

View full text Add to dashboard Cite

Load forecasting is a vital part of smart grids for predicting the required electrical power using artificial intelligence (AI). Deep learning is broadly used for load forecasting in the smart grid using the artificial neural network (ANN). Generally, computing the deep learning in the smart grid requires massive data aggregation or centralization and significant computational time. This paper presents a survey of deep learning-based load forecasting techniques from 2015 to 2020. This survey discusses the studies based on their deep learning techniques, Distributed Deep Learning (DDL) techniques, Back Propagation (BP) based works, and non-BP based works in the load forecasting process. Consequent to the survey, it was determined that data aggregation dependency would be beneficial for reducing computational time in load forecasting. Therefore, a conceptual model of DDL for smart grids has been presented, where the HSIC (Hilbert-Schmidt Independence Criterion) Bottleneck technique has been incorporated to provide higher accuracy.

show abstract

A Cascaded Feature Pyramid Network With Non-Backward Propagation for Facial Expression Recognition

Cited by 13 publications

References 30 publications

Feature Pyramid Network for Multi-task Affective Analysis

Feature Pyramid Network for Multi-task Affective Analysis

A Novel Approach to Maritime Image Dehazing Based on a Large Kernel Encoder–Decoder Network with Multihead Pyramids

HSIC Bottleneck Based Distributed Deep Learning Model for Load Forecasting in Smart Grid With a Comprehensive Survey

Contact Info

Product

Resources

About