基于残差结构的GAN网络的显著性预测研究

赖远哲; 陈向阳; 李旭东; 付星堡; 曹倩倩

Chinese

您当前的位置：

首页 >

文章列表页 >

基于残差结构的GAN网络的显著性预测研究

更新时间：2026-09-04

- 基于残差结构的GAN网络的显著性预测研究
- Research on saliency prediction of GAN network based on residual structure
- 微电子学与计算机 2021年38卷第8期页码：95-100
- 作者机构：
  
  1. 武汉工程大学机构计算机科学与工程学院,湖北,武汉,430205
  2. 武汉工程大学智能机器人湖北省重点实验室,湖北,武汉,430205
- 作者简介：
- 基金信息：
  
  武汉工程大学教育创新基金 CX2019234
- DOI：
  中图分类号：
- 纸质出版：2021
- 稿件说明：
移动端阅览
赖远哲, 陈向阳, 李旭东, 付星堡, 曹倩倩. 基于残差结构的GAN网络的显著性预测研究[J]. 微电子学与计算机, 2021, 38(8): 95-100.

LAI Yuanzhe, CHEN Xiangyang, LI Xudong, et al. Research on saliency prediction of GAN network based on residual structure[J]. 2021, 38(8): 95-100.
赖远哲, 陈向阳, 李旭东, 付星堡, 曹倩倩. 基于残差结构的GAN网络的显著性预测研究[J]. 微电子学与计算机, 2021, 38(8): 95-100. DOI：

LAI Yuanzhe, CHEN Xiangyang, LI Xudong, et al. Research on saliency prediction of GAN network based on residual structure[J]. 2021, 38(8): 95-100. DOI：

摘要

优化了简单生成对抗网络结构，用于更有效的通过对抗性实例训练得到视觉显着性图，减少假阳性产生和提高显著性.网络模型仍遵循传统生成对抗网络结构，第一阶段是由一个使用残差结构建的生成器组成，该模型的权值由显著图的下采样版本的二分类交叉熵损失(BCE)的反向传播计算得到的，训练得到更有效的显著图.预测结果由受训练的判别器网络进行生成阶段生成的显著图与真值图之间的二值分类处理.实验展示了改进生成对抗网络中的生成器的预测显著图的能力对整个网络性能提升，相较于其他显著图预测模型也有一定领先.

Abstract

The structure of simple generated countermeasure network is optimized

whichis used to obtain visual saliency map more effectively through antagonistic case training

so as to reduce false positive and improve saliency. The network model still follows the traditional generation countermeasure network structure. In the first stage

it is composed of a generator built with residual structure. The weight of the model is calculated by the back-propagation of the binary cross entropy loss (BCE) of the down sampling version of saliency map

and the more effective saliency map is obtained by training. The prediction results are classified by the trained discriminator network between saliency map and truth graph. The experiment shows that the improved ability to generate predictive saliency map of generators in the countermeasure network can improve the performance of the whole network

and it is also ahead of other saliency map prediction models.

关键词

Keywords

references

KüMMERER M, THEIS L, BETHGE M. Deep gaze i: Boosting saliency prediction with feature maps trained on imagenet[J]. arXiv preprint arXiv: 1411.1045, 2014.

HAREL J, KOCH C, PERONA P. Graph-based visual saliency[C]//Proceedings of the 19th International Conference on Neural Information Processing Systems. Cambridge: MIT Press, 2006: 545-552.

CORNIA M, BARALDI L, SERRA G, et al. A deep multi-level network for saliency prediction[C]//2016 23rd International Conference on Pattern Recognition (ICPR). IEEE, 2016: 3488-3493.

SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv: 1409.1556, 2014.

LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: Common objects in context[C]//European Conference on Computer Vision. Cham: Springer, 2014: 740-755. DOI: 10.1007/978-3-319-10602-1_48.

VIG E, DORR M, COX D. Large-scale optimization of hierarchical features for saliency prediction in natural images[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Columbus: IEEE, 2014: 2798-2805. DOI: 10.1109/CVPR.2014.358.

GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Advances in neuralinformation processing systems. 2014: 2672-2680.

JOHNSON J, ALAHI A, LI F F. Perceptual losses for real-time style transfer and super-resolution[C]//European Conference on Computer Vision. Cham: Springer, 2016: 694-711. DOI: 10.1007/978-3-319-46475-6_43.

CORNIA M, BARALDI L, SERRA G, et al. Predicting human eye fixations via an LSTM-based saliency attentive model[J]. IEEE Transactions on Image Processing, 2018, 27(10): 5142-5154. DOI: 10.1109/TIP.2018.2851672.

TREISMAN A M, GELADE G. A feature-integration theory of attention[J]. Cognitive Psychology, 1980, 12(1): 97-136. DOI: 10.1016/0010-0285(80)90005-5.

ITTI L, KOCH C, NIEBUR E. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(11): 1254-1259. DOI: 10.1109/34.730558.

GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Proceedings of the 27th International Conference onNeuralInformation Processing Systems. Montreal: MIT Press, 2014: 2672-2680.

PAN J T, SAYROL E, GIR?-I-NIETO X, et al. SalGAN: Visual saliency prediction with generative adversarial networks[C]//CVPR SUNw: Scene Understanding Workshop 2017. Hawaii: IEEE, 2017.

CORNIA M, BARALDI L, SERRA G, et al. A deep multi-level network for saliency prediction[C]//2016 23rd International Conference on Pattern Recognition (ICPR). Cancun, IEEE, 2016: 3488-3493. DOI: 10.1109/ICPR.2016.7900174.

JUDD T, EHINGER K, DURAND F, et al. Learning to predict where humans look[C]//2009 IEEE 12th International Conference on Computer Vision. Kyoto: IEEE, 2009: 2106-2113. DOI: 10.1109/ICCV.2009.5459462.

JIANG M, HUANG S S, DUAN J Y, et al, SALICON: Saliency in context[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Boston: IEEE, 2015. DOI: 10.1109/CVPR.2015.7298710.

LIU N, HAN J W. A deep spatial contextual long-term recurrent convolutional network for saliency detection[J]. IEEE Transactions on Image Processing, 2018, 27(7): 3264-3274. DOI: 10.1109/TIP.2018.2817047.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向处理器分支预测单元的Spectre攻击轻量化防御方法

基于区块链的AI生成内容溯源框架设计研究

基于MSS-YOLO-MPHands融合架构的装配手部动作识别研究

低功耗设计的双链电源关断策略的实现与验证

注意力机制与改进密集卷积引导的信息隐藏模型