深度学习背景下视觉显著性物体检测综述

王自全; 张永生; 于英; 闵杰; 田浩

doi:10.11834/jig.200649

综述 | 浏览量 : 0 下载量: 257 CSCD: 6

PDF
导出
分享
收藏
专辑

深度学习背景下视觉显著性物体检测综述
Review of deep learning based salient object detection
2022年27卷第7期页码：2112-2128
收稿：2020-11-13，

修回：2021-3-15，

录用：2021-3-22，

纸质出版：2022-07-16
DOI： 10.11834/jig.200649
稿件说明：

移动端阅览

王自全, 张永生, 于英, 闵杰, 田浩. 深度学习背景下视觉显著性物体检测综述[J]. 中国图象图形学报, 2022,27(7):2112-2128. DOI： 10.11834/jig.200649.

Ziquan Wang, Yongsheng Zhang, Ying Yu, Jie Min, Hao Tian. Review of deep learning based salient object detection[J]. Journal of Image and Graphics, 2022, 27(7): 2112-2128. DOI： 10.11834/jig.200649.

摘要

视觉显著性物体检测是对人类视觉和认知系统的模拟，而深度学习则是对人类大脑计算方式的模拟，将两者有机结合可以有效推动计算机视觉的发展。视觉显著性物体检测的任务是从图像中定位并提取具有明确轮廓的显著性物体实例。随着深度学习的发展，视觉显著性物体检测的精度和效率都得到巨大提升，但仍然面临改进主流算法性能、减少对像素级标注样本的依赖等主要挑战。针对上述挑战，本文从视觉显著性物体检测思想与深度学习方法融合策略的角度对相关论述进行分类总结。1）分析传统显著性物体检测方法带来的启示及其缺点，指出视觉显著性物体检测的核心思路为多层次特征的提取、融合与修整；2）从改进特征编码方式与信息传递结构、提升边缘定位精度、改善注意力机制、提升训练稳定性和控制噪声的角度对循环卷积神经网络、全卷积神经网络和生成对抗网络3种主流算法的性能提升进行分析，从优化弱监督样本处理模块的角度分析了减少对像素级标注样本依赖的方法；3）对协同显著性物体检测、多类别图像显著性物体检测以及未来的研究问题和方向进行介绍，并给出了可能的解决思路。

Abstract

Salient object detection (SOD) visual technology is a simulation of human vision and cognitive system nowadays. Current deep learning method is a computational simulation for human brain. Traditional SOD methods are required to design complicated hand-craft features to extract multi-level features

and then use machine learning or other methods for fusion and refinement. Each step of SOD can be internalized into the deep learning based neural network model related to a variety of algorithms. To provide reference for our intelligent SOD methods

recent SOD are sorted out from the perspective of principles

basic ideas and algorithms in detail. First

we briefly review the classic framework of traditional SOD methods to extract SOD technology like multi-level features fusion. Current challenges are related to time-consuming preprocessing

complex feature designing and lack of robust. Traditional methods are based on contrasting features

which tend to identify the boundary of the object and the corresponding internal noise. However

the SOD task is more concerned with the scope of the object and constrained of the internal homogeneous area to be suppressed. In addition

the spatial domain features extractions are disturbed of the effects of light and complex background

it is difficult to be integrated with other features effectively. These unstable issues are resulted in. Next

we analyzes a sort of fully supervised implementation architectures for significant deep learning based object detection in the context of the early fusion model

series of recurrent convolution neural network (CNN) architecture

series of full convolution network architecture as well as the feature extraction and fusion enhanced attention mechanism. The internal mechanism and connection of these methods are discussed. "The early fusion model" refers to the fusion strategy of traditional features and deep learning features in terms of artificial rules (such as vector stitching) in 2015. This strategic artificial feature fusion rules are lack of theories and mechanisms. CNN method is only used for high-level features extraction. Each super pixel needs to be traversed and input into the neural network

which is time-consuming. Recurrent CNN constant updates the recognition results to identify the target through introducing the forgetting mechanism. Thanks to this

multi-level features can naturally aggregate with each other using less parameters

which can achieve a better result than the single feed forward network. Full convolution network (FCN) is qualified for end-to-end multi-classification tasks at pixel level in complex background greatly enhanced the detection capability. To aggregate multi-level features

current researches are conducted based on FCN and illustrated a large number of customized models based on multiple strategies

including improving the fusion method in the network

compensating for the network's extraction accuracy of boundary information. Recent the attention mechanism module have become a useful supplement for neural network model. Not only does attention mechanism improve the precision of salient object detection

but also makes the thought of "salient" deliberated that it can only be applied in the classification task at pixel level. So the "salient concepts" can be used in object detection and lightweight model. Thirdly

The weak supervision and multi-task issues have their potentials because the training of full supervision salient object detection method requires expensive pixel-level annotation. Since the task-oriented CNN classification can focus and locate objects with image based tag semantics in the context of detailed salient maps optimization. Meanwhile

the sample updating method needs to be designed because the weakly supervised samples are insufficient to the refinement after generating initial salient map. At last

we introduce the application and development of generative adversarial network (GAN) and graph neural network (GNN) in SOD. Thanks to neural network theory

GNN and GAN have also been applied to SOD task. Based on of summarizing the existing methods

future SOD are predicted like feature fusion mode improvement

collaborative significant object detection

weak supervision and multi-task strategy

and multi-categories image significance detection. In these scenarios

the data has a more complex or fuzzy distribution (e.g.

no longer subject to Euclidean spatial distribution). The solution should be more capable to describe the features further.

关键词

Keywords

references

Achanta R, Hemami S, Estrada F and Süsstrunk S. 2009. Frequency-tuned salient region detection//Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, USA: IEEE: 1597-1604 [ DOI: 10.1109/CVPR.2009.5206596 10.1109/CVPR.2009.5206596 ]

Achanta R, Shaji A, Smith K, Lucchi A, Fua P and Süsstrunk S. 2012. SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11): 2274-2282 [DOI: 10.1109/TPAMI.2012.120]

Borji A and Itti L. 2013. State-of-the-art in visual attention modeling. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(1): 185-207 [DOI: 10.1109/TPAMI.2012.89]

Bruce N D B and Tsotsos J K. 2005. Saliency based on information maximization//Proceedings of the 18th International Conference on Neural Information ProcessingSystems. Vancouver, Canada: MIT Press: 155-162

Chattopadhyay A, Sarkar A, Howlader P and Balasubramanian V. 2018. Grad-CAM++: generalized gradient-based visual explanations for deep convolutional networks [EB/OL]. [2020-11-13] . https://arxiv.org/pdf/1710.11063v1.pdf https://arxiv.org/pdf/1710.11063v1.pdf

Chen S H, Tan X L, Wang B, Lu H C, Hu X L and Fu Y. 2020. Reverse attention-based residual network for salient object detection. IEEE Transactions on Image Processing, 29: 3763-3776 [DOI: 10.1109/TIP.2020.2965989]

Cheng M M, Zhang G X, Mitra N J, Huang X L and Hu S M. 2011. Global contrast based salient region detection//Proceedings of 2011 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Colorado Springs, USA: IEEE: 409-416 [ DOI: 10.1109/CVPR.2011.5995344 10.1109/CVPR.2011.5995344 ]

Deng Z J, Hu X W, Zhu L, Xu X M, Qin J, Han G Q and Heng P A. 2018. R 3 Net: recurrent residual refinement network for saliency detection//Proceedings of the 27th International Joint Conference on Artificial Intelligence. Stockholm, Sweden: AAAI Press: 684-690

Fu J, Liu J, Tian H J, Li Y, Bao Y J, Fang Z W and Lu H Q. 2019. Dual attention network for scene segmentation//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, USA: IEEE: 3141-3149 [ DOI: 10.1109/CVPR.2019.00326 10.1109/CVPR.2019.00326 ]

Goodfellow I J, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A and Bengio Y. 2014. Generative adversarial nets//Proceedings of the 27th International Conference on Neural Information Processing Systems. Montreal, Canada: MIT Press: 2672-2680

He K M, Zhang X Y, Ren S Q and Sun J. 2016. Deep residual learning for image recognition//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, USA: IEEE: 770-778 [ DOI: 10.1109/CVPR.2016.90 10.1109/CVPR.2016.90 ]

Hochreiter S and Schmidhuber J. 1997. Long short-term memory. Neural Computation, 9(8): 1735-1780 [DOI: 10.1162/neco.1997.9.8.1735]

Hou Q B, Cheng M M, Hu X W, Borji A, Tu Z W and Torr P H S. 2019a. Deeply supervised salient object detection with short connections. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(4): 815-828 [DOI: 10.1109/TPAMI.2018.2815688]

Hou Q B, Liu J J, Cheng M M, Borji A and Torr P H S. 2019b. Three birds one stone: a unified framework for salient object segmentation, edge detection and skeleton extraction [EB/OL]. [2020-11-13] . https://arxiv.org/pdf/1803.09860.pdf https://arxiv.org/pdf/1803.09860.pdf

Hou X D and Zhang L Q. 2007. Saliency detection: a spectral residual approach//Proceedings of 2007 IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, USA: IEEE: 1-8 [ DOI: 10.1109/CVPR.2007.383267 10.1109/CVPR.2007.383267 ]

Hu J, Shen L, Albanie S, Sun G and Wu E H. 2020. Squeeze-and-excitation networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(8): 2011-2023 [DOI: 10.1109/TPAMI.2019.2913372]

Hu X W, Fu C W, Zhu L, Wang T Y and Heng P A. 2021. SAC-net: spatial attenuation context for salient object detection. IEEE Transactions on Circuits and Systems for Video Technology, 31(3): 1079-1090 [DOI: 10.1109/TCSVT.2020.299-5220]

Ke W, Chen J, Jiao J B, Zhao G Y and Ye Q X. 2017. SRN: side-output residual network for object symmetry detection in the wild//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE: 302-310 [ DOI: 10.1109/CVPR.2017.40 10.1109/CVPR.2017.40 ]

Krähenbühl P and Koltun V. 2012. Efficient inference in fully connected CRFs with Gaussian edge potentials [EB/OL]. [2020-11-13] . https://arxiv.org/pdf/1210.5644.pdf https://arxiv.org/pdf/1210.5644.pdf

Krizhevsky A, Sutskever I and Hinton G E. 2012. ImageNet classification with deep convolutional neural networks//Proceedings of the 25th International Conference on Neural Information Processing Systems. Lake Tahoe, USA: Curran Associates Inc. : 1097-1105

Lafferty J, McCallum A and Pereira F C N. 2001. Conditional random fields: probabilistic models for segmenting and labeling sequence data//Proceedings of the 18th International Conference on Machine Learning. San Francisco, USA: Morgan Kaufmann Publishers Inc. : 282-289

Lee G, Tai Y W and Kim J. 2016. Deep saliency with encoded low level distance map and high level features//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA: IEEE: 660-668 [ DOI: 10.1109/CVPR.2016.78 10.1109/CVPR.2016.78 ]

Li G B, Xie Y and Lin L. 2018. Weakly supervised salient object detection using image labels [EB/OL]. [2020-11-13] . https://arxiv.org/pdf/1803.06503.pdf https://arxiv.org/pdf/1803.06503.pdf

Li G B and Yu Y Z. 2015. Visual saliency based on multiscale deep features//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, USA: IEEE: 5455-5463 [ DOI: 10.1109/CVPR.2015.7299184 10.1109/CVPR.2015.7299184 ]

Li G B and Yu Y Z. 2016. Deep contrast learning for salient object detection//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA: IEEE: 478-487 [ DOI: 10.1109/CVPR.2016.58 10.1109/CVPR.2016.58 ]

Li G B, Xie Y, Lin L and Yu Y Z. 2017. Instance-level salient object segmentation//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE: 247-256 [ DOI: 10.1109/CVPR.2017.34 10.1109/CVPR.2017.34 ]

Li X, Zhao L M, Wei L N, Yang M H, Wu F, Zhuang Y T, Ling H B and Wang J D. 2016. DeepSaliency: multi-task deep neural network model for salient object detection. IEEE Transactions on Image Processing, 25(8): 3919-3930 [DOI: 10.1109/TIP.2016.2579306]

Li Z, Lang C Y, Liew J, Hou Q B, Li Y D and Feng J S. 2020. Cross-layer feature pyramid network for salient object detection [EB/OL]. [2020-02-25] . https://arxiv.org/pdf/2002.10864.pdf https://arxiv.org/pdf/2002.10864.pdf

Liang M and Hu X L. 2015. Recurrent convolutional neural network for object recognition//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston, USA: IEEE: 3367-3375 [ DOI: 10.1109/CVPR.2015.7298958 10.1109/CVPR.2015.7298958 ]

Lin T Y, Dollár P, Girshick R, He K M, Hariharan B and Belongie S. 2017. Feature pyramid networks for object detection//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, USA: IEEE: 936-944 [ DOI: 10.1109/CVPR.2017.106 10.1109/CVPR.2017.106 ]

Liu J J, Hou Q B, Cheng M M, Feng J S and Jiang J M. 2019. A simple pooling-based design for real-time salient object detection//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, USA: IEEE: 3912-3921 [ DOI: 10.1109/CVPR.2019.00404 10.1109/CVPR.2019.00404 ]

Liu N and Han J W. 2016. DHSNet: deep hierarchical saliency network for salient object detection//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA: IEEE: 678-686 [ DOI: 10.1109/CVPR.2016.80 10.1109/CVPR.2016.80 ]

Liu N, Han J W and Yang M H. 2018. PiCANet: pixel-wise contextual attention learning for accurate saliency detection [EB/OL] . [2020-11-13]. https://arxiv.org/pdf/1812.06314v1.pdf https://arxiv.org/pdf/1812.06314v1.pdf

Liu T, Yuan Z J, Sun J, Wang J D, Zheng N N, Tang X O and Shum H Y. 2011. Learning to detect a salient object. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(2): 353-367 [DOI: 10.1109/TPAMI.2010.70]

Luo Z M, Mishra A, Achkar A, Eichel J, Li S Z and Jodoin P M. 2017. Non-local deep features for salient object detection//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, USA: IEEE: 6593-6601 [ DOI: 10.1109/CVPR.2017.698 10.1109/CVPR.2017.698 ]

Maninis K, Pont-Tuset J, Arbeláez P and Van Gool L. 2018. Convolutional oriented boundaries: from image segmentation to high-level tasks, IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(4): 819-833 [ DOI: 10.1109/TPAMI.2017.2700300 10.1109/TPAMI.2017.2700300 ]

Mao Q, Lee H Y, Tseng H Y, Ma S W and Yang M H. 2019. Mode seeking generative adversarial networks for diverse image synthesis//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, USA: IEEE: 1429-1437 [ DOI: 10.1109/CVPR.2019.00152 10.1109/CVPR.2019.00152 ]

Marchesotti L, Cifarelli C and Csurka G. 2009. A framework for visual saliency detection with applications to image thumb nailing//Proceedings of 2009 IEEE International Conference on Computer Vision. Kyoto, Japan: IEEE: 2232-2239 [ DOI: 10.1109/ICCV.2009.5459467 10.1109/ICCV.2009.5459467 ]

Mukherjee P, Sharma M, Makwana M, Singh A P, Upadhyay A, Trivedi A, Lall B and Chaudhury S. 2019. DSAL-GAN: denoising based saliency prediction with generative adversarial networks [EB/OL]. [2020-11-13] . https://arxiv.org/pdf/1904.01215.pdf https://arxiv.org/pdf/1904.01215.pdf

Mumford D and Shah J. 1989. Optimal approximations by piecewise smooth functions and associated variational problems. Communications on Pure and Applied Mathematics, 42(5): 577-685 [DOI: 10.1002/cpa.3160420503]

Odena A, Dumoulin V and Olah C. 2016. Deconvolution and Checkerboard Artifacts. Distill, 1(10) [DOI: 10.23915/distill.00003]

Pan J T, Ferrer C C, McGuinness K, O'Connor N E, Torres J, Sayrol E and Giró-i-Nieto X. 2018. SalGAN: visual saliency prediction with generative adversarial networks [EB/OL]. [2020-11-13] . https://arxiv.org/pdf/1701.01081.pdf https://arxiv.org/pdf/1701.01081.pdf

Perazzi F, Krähenbühl P, Pritch Y and Hornung A. 2012. Saliency filters: contrast based filtering for salient region detection//Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence, USA: IEEE: 733-740 [ DOI: 10.1109/CVPR.2012.6247743 10.1109/CVPR.2012.6247743 ]

Qin X B, Zhang Z C, Huang C Y, Gao C, Dehghan M and Jagersand M. 2019. BASNet: boundary-aware salient object detection//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, USA: IEEE: 7471-7481 [ DOI: 10.1109/CVPR.2019.00766 10.1109/CVPR.2019.00766 ]

Rother C, Bordeaux L, Hamadi Y and Blake A. 2006. AutoCollage. ACM Transactions on Graphics, 25(3): 847-852 [DOI: 10.1145/1141911.1141965]

Selvaraju R R, Das A, Vedantam R, Cogswell M, Parikh D and Batra D. 2017. Grad-CAM: why did you say that? [EB/OL]. [2020-11-13] . https://arxiv.org/pdf/1611.07450v2.pdf https://arxiv.org/pdf/1611.07450v2.pdf

Shelhamer E, Long J and Darrell T. 2017. Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(4): 640-651 [DOI: 10.1109/TPAMI.2016.2572683]

Simonyan K and Zisserman A. 2015. Very deep convolutional networks for large-scale image recognition [EB/OL]. [2020-11-13] . http://arxiv.org/pdf/1409.1556.pdf http://arxiv.org/pdf/1409.1556.pdf

Wang J D, Jiang H Z, Yuan Z J, Cheng M M, Hu X W and Zheng N N. 2017a. Salient object detection: a discriminative regional feature integration approach. International Journal of Computer Vision, 123(2): 251-268 [DOI: 10.1007/s11263-016-0977-3]

Wang L J, Lu H C, Wang Y F, Feng M Y, Wang D, Yin B C and Ruan X. 2017b. Learning to detect salient objects with image-level supervision//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, USA: IEEE: 3796-3805 [ DOI: 10.1109/CVPR.2017.404 10.1109/CVPR.2017.404 ]

Wang L Z, Wang L J, Lu H C, Zhang P P and Ruan X. 2016. Saliency detection with recurrent fully convolutional networks//Proceedings of the 14th European Conference on Computer Vision. Amsterdam, the Netherlands: Springer: 825-841 [ DOI: 10.1007/978-3-319-46493-0_50 10.1007/978-3-319-46493-0_50 ]

Wang W, Wang Y Z, Huang Q M and Gao W. 2010. Measuring visual saliency by site entropy rate//Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco, USA: IEEE: 2368-2375 [ DOI: 10.1109/CVPR.2010.5539927 10.1109/CVPR.2010.5539927 ]

Wu H F, Li G B and Luo X N. 2014. Weighted attentional blocks for probabilistic object tracking. The Visual Computer, 30(2): 229-243 [DOI: 10.1007/s00371-013-0823-3]

Wu R M, Feng M Y, Guan W L, Wang D, Lu H C and Ding E R. 2020. A mutual learning method for salient object detection with intertwined multi-supervision//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, USA: IEEE: 8142-8151 [ DOI: 10.1109/CVPR.2019.00834 10.1109/CVPR.2019.00834 ]

Xie S N and Tu Z W. 2017. Holistically-nested edge detection. International Journal of Computer Vision, 125(1/3): 3-18 [DOI: 10.1007/s11263-017-1004-z]

Yan Q, Xu L, Shi J P and Jia J Y. 2013. Hierarchical saliency detection//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland, USA: IEEE: 1155-1162 [ DOI: 10.1109/CVPR.2013.153 10.1109/CVPR.2013.153 ]

Yang C, Zhang L H, Lu H C, Ruan X and Yang M H. 2013. Saliency detection via graph-based manifold ranking//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland, USA: IEEE: 3166-3173 [ DOI: 10.1109/CVPR.2013.407 10.1109/CVPR.2013.407 ]

Zeng Y, Zhuge Y Z, Lu H C, Zhang L H, Qian M Y and Yu Y Z. 2019. Multi-source weak supervision for saliency detection//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, USA: IEEE: 6067-6076 [ DOI: 10.1109/CVPR.2019.00623 10.1109/CVPR.2019.00623 ]

Zhang J, Yu X, Li A X, Song P P, Liu B W and Dai Y C. 2020a. Weakly-supervised salient object detection via scribble annotations//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, USA: IEEE: 12543-12552 [ DOI: 10.1109/CVPR42600.2020.01256 10.1109/CVPR42600.2020.01256 ]

Zhang K H, Li T P, Shen S W, Liu B, Chen J and Liu Q S. 2020b. Adaptive graph convolutional network with attention graph clustering for co-saliency detection//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, USA: IEEE: 9047-9056 [ DOI: 10.1109/CVPR42600.2020.00907 10.1109/CVPR42600.2020.00907 ]

Zhang L, Dai J, Lu H C, He Y and Wang G. 2018. A bi-directional message passing model for salient object detection//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE: 1741-1750 [ DOI: 10.1109/CVPR.2018.00187 10.1109/CVPR.2018.00187 ]

Zhang P P, Wang D, Lu H C, Wang H Y and Ruan X. 2017a. Amulet: aggregating multi-level convolutional features for salient object detection//Proceedings of 2017 IEEE International Conference on Computer Vision (ICCV). Venice, Italy: IEEE: 202-211 [ DOI: 10.1109/ICCV.2017.31 10.1109/ICCV.2017.31 ]

Zhang P P, Wang D, Lu H C, Wang H Y and Yin B C. 2017b. Learning uncertain convolutional features for accurate saliency detection//Proceedings of 2017 IEEE International Conference on Computer Vision (ICCV). Venice, Italy: IEEE: 212-221 [ DOI: 10.1109/ICCV.2017.32 10.1109/ICCV.2017.32 ]

Zhao T and Wu X Q. 2019. Pyramid feature attention network for saliency detection//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, USA: IEEE: 3080-3089 [ DOI: 10.1109/CVPR.2019.00320 10.1109/CVPR.2019.00320 ]

Zhou B L, Khosla A, Lapedriza A, Oliva A and Torralba A. 2016. Learning deep features for discriminative localization//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, USA: IEEE: 2921-2929 [ DOI: 10.1109/CVPR.2016.319 10.1109/CVPR.2016.319 ]

Zhou S P, Zhang J Y, Wang J J, Wang F and Huang D. 2019. SE 2 Net: siamese edge-enhancement network for salient object detection [EB/OL]. [2020-11-13] . https://www.arxiv.org/pdf/1904.00048.pdf https://www.arxiv.org/pdf/1904.00048.pdf .

Zhou Z Q, Wang Z, Lu H C, Wang S and Sun M J. 2020. Multi-type self-attention guided degraded saliency detection. Proceedings of the AAAI Conference on Artificial Intelligence, 34(7): 13082-13089 [DOI: 10.1609/aaai.v34i07.7010]