{"type":"ScholarlyArticle","title":"Automatic Gating of Attributes in Deep Structure","authors":[{"name":"Xiaoming Jin","slug":"xiaoming-jin","given":"Xiaoming","family":"Jin","affiliation":"School of Software , Tsinghua University , Beijing , China"},{"name":"Tao He","slug":"tao-he","given":"Tao","family":"He","affiliation":"School of Software , Tsinghua University , Beijing , China"},{"name":"Cheng Wan","slug":"cheng-wan","given":"Cheng","family":"Wan","affiliation":"Baidu Corporation , Beijing , China"},{"name":"Lan Yi","slug":"lan-yi","given":"Lan","family":"Yi","affiliation":"Department of DevNet , Cisco Systems"},{"name":"Guiguang Ding","slug":"guiguang-ding","given":"Guiguang","family":"Ding","affiliation":"School of Software , Tsinghua University , Beijing , China"},{"name":"Dou Shen","slug":"dou-shen","given":"Dou","family":"Shen","affiliation":"Baidu Corporation , Beijing , China"}],"abstract":"Deep structure has been widely applied in a large variety of fields for its excellence of representing data. Attributes are a unique type of data descriptions that have been successfully utilized in numerous tasks to enhance performance. However, to introduce attributes into deep structure is complicated and challenging, because different layers in deep structure accommodate features of different abstraction levels, while different attributes may naturally represent the data in different abstraction levels. This demands adaptively and jointly modeling of attributes and deep structure by carefully examining their relationship. Different from existing works that treat attributes straightforwardly as the same level without considering their abstraction levels, we can make better use of attributes in deep structure by properly connecting them. In this paper, we move forward along this new direction by proposing a deep structure named Attribute Gated Deep Belief Network (AG-DBN) that includes a tunable attribute-layer gating mechanism and automatically learns the best way of connecting attributes to appropriate hidden layers. Experimental results on a manually-labeled subset of ImageNet, a-Yahoo and a-Pascal data set justify the superiority of AG-DBN against several baselines including CNN model and other AG-DBN variants. Specifically, it outperforms the CNN model, VGG19, by significantly reducing the classification error from 26.70% to 13.56% on a-Pascal.","doi":"10.24963/ijcai.2018/319","url":"https://ijcai.org/proceedings/2018/319","pdf":"https://ijcai.org/proceedings/2018/0319.pdf","markdown":"https://ijcai.org/proceedings/2018/319.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/319","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Machine Learning","track":"Main track","number":319,"pages":{"first":2305,"last":2311},"keywords":["Machine Learning: Neural Networks","Machine Learning: Deep Learning","Machine Learning: Classification"],"videos":[],"references":[{"position":1,"raw":"[Abdulnabi et al., 2015] Abrar H Abdulnabi, Gang Wang, Jiwen Lu, and Kui Jia. Multi-task cnn model for at- tribute prediction. IEEE Transactions on Multimedia, 17(11):1949-1959, 2015.","title":"Multi-task cnn model for attribute prediction","authors":"Gang Abrar H Abdulnabi, Jiwen Wang, Kui Lu, Jia","year":"2015","venue":"IEEE Transactions on Multimedia","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bahdanau et al., 2014] Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473, 2014.","title":"Neural machine translation by jointly learning to align and translate","authors":"Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bengio, 2009] Yoshua Bengio. Learning deep architectures for ai. Foundations and trends R in Machine Learning, 2(1):1-127, 2009.","title":"Learning deep architectures for ai","authors":"Yoshua Bengio","year":"2009","venue":"Foundations and trends R in Machine Learning","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bishop, 2006] Christopher M Bishop. Pattern recognition. Machine Learning, 128, 2006.","title":"Pattern recognition","authors":"M Christopher, Bishop","year":"2006","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Collobert et al., 2011] Ronan Collobert, Jason Weston, Léon Bottou, Michael Karlen, Koray Kavukcuoglu, and Pavel Kuksa. Natural language processing (almost) from scratch. Journal of Machine Learning Research, 12(Aug):2493-2537, 2011.","title":"Natural language processing (almost) from scratch","authors":"Ronan Collobert, Jason Weston, Léon Bottou, Michael Karlen, Koray Kavukcuoglu, Pavel Kuksa","year":"2011","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Deng et al., 2013] Li Deng, Geoffrey Hinton, and Brian Kingsbury. New types of deep neural network learn- ing for speech recognition and related applications: An overview. In 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pages 8599- 8603. IEEE, 2013.","title":"New types of deep neural network learning for speech recognition and related applications: An overview","authors":"Li Deng, Geoffrey Hinton, Brian Kingsbury","year":"2013","venue":"IEEE International Conference on Acoustics, Speech and Signal Processing","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Deng, 2014] Li Deng. A tutorial survey of architectures, algorithms, and applications for deep learning. APSIPA Transactions on Signal and Information Processing, 3:e2, 2014.","title":"A tutorial survey of architectures, algorithms, and applications for deep learning","authors":"Li Deng","year":"2014","venue":"APSIPA Transactions on Signal and Information Processing","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Farhadi et al., 2009] Ali Farhadi, Ian Endres, Derek Hoiem, and David Forsyth. Describing objects by their attributes. In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, pages 1778-1785. IEEE, 2009.","title":"Describing objects by their attributes","authors":"Ali Farhadi, Ian Endres, Derek Hoiem, David Forsyth","year":"2009","venue":"Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recog- nition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770-778, 2016.","title":"Deep residual learning for image recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2016","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Hinton, 2002] Geoffrey E. Hinton. Training products of ex- perts by minimizing contrastive divergence. Neural com- putation, 14 8:1771-800, 2002.","title":"Training products of experts by minimizing contrastive divergence","authors":"Geoffrey E Hinton","year":"2002","venue":"Neural computation","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Hinton, 2009] Geoffrey E Hinton. Deep belief networks. Scholarpedia, 4(5):5947, 2009.","title":"Deep belief networks","authors":"Geoffrey E Hinton","year":"2009","venue":"Scholarpedia","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Hinton, 2010] Geoffrey Hinton. A practical guide to train- ing restricted boltzmann machines. Momentum, 9(1):926, 2010.","title":"A practical guide to training restricted boltzmann machines","authors":"Geoffrey Hinton","year":"2010","venue":"Momentum","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Hwang et al., 2011] Sung Ju Hwang, Fei Sha, and Kristen Grauman. Sharing features between objects and their at- tributes. In Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on, pages 1761-1768. IEEE, 2011.","title":"Sharing features between objects and their attributes","authors":"Sung Ju Hwang, Fei Sha, Kristen Grauman","year":"2011","venue":"Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Krizhevsky et al., 2012] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classification with deep convolutional neural networks. In Advances in neural in- formation processing systems, pages 1097-1105, 2012.","title":"Imagenet classification with deep convolutional neural networks","authors":"Krizhevsky","year":"2012","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Lampert et al., 2009] Christoph H Lampert, Hannes Nick- isch, and Stefan Harmeling. Learning to detect unseen object classes by between-class attribute transfer. In Com- puter Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, pages 951-958. IEEE, 2009.","title":"Learning to detect unseen object classes by between-class attribute transfer","authors":"Hannes Christoph H Lampert, Stefan Nickisch, Harmeling","year":"2009","venue":"Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[LeCun et al., 2015] Yann LeCun, Yoshua Bengio, and Ge- offrey Hinton. Deep learning. nature, 521(7553):436, 2015.","title":"Deep learning","authors":"Yann Lecun, Yoshua Bengio, Geoffrey Hinton","year":"2015","venue":"nature","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Lee et al., 2009] Honglak Lee, Roger Grosse, Rajesh Ran- ganath, and Andrew Y Ng. Convolutional deep belief net- works for scalable unsupervised learning of hierarchical representations. In Proceedings of the 26th annual inter- national conference on machine learning, pages 609-616. ACM, 2009.","title":"Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations","authors":"Lee","year":"2009","venue":"Proceedings of the 26th annual international conference on machine learning","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Mnih et al., 2012] Volodymyr Mnih, Hugo Larochelle, and Geoffrey E Hinton. Conditional restricted boltzmann ma- chines for structured output prediction. arXiv preprint arXiv:1202.3748, 2012.","title":"Conditional restricted boltzmann machines for structured output prediction","authors":"Volodymyr Mnih, Hugo Larochelle, Geoffrey E Hinton","year":"2012","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Mohamed et al., 2012] Abdel-rahman Mohamed, George E Dahl, and Geoffrey Hinton. Acoustic modeling using deep belief networks. IEEE Transactions on Audio, Speech, and Language Processing, 20(1):14-22, 2012.","title":"Acoustic modeling using deep belief networks","authors":"Mohamed","year":"2012","venue":"IEEE Transactions on Audio, Speech, and Language Processing","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Russakovsky et al., 2015] Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, et al. Imagenet large scale visual recogni- tion challenge. International Journal of Computer Vision, 115(3):211-252, 2015.","title":"Imagenet large scale visual recognition challenge","authors":"Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein","year":"2015","venue":"International Journal of Computer Vision","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Simonyan and Zisserman, 2014] Karen Simonyan and An- drew Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.","title":"Very deep convolutional networks for large-scale image recognition","authors":"Karen Simonyan, Andrew Zisserman","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Sohn et al., 2013] Kihyuk Sohn, Guanyu Zhou, Chansoo Lee, and Honglak Lee. Learning and selecting features jointly with point-wise gated boltzmann machines. In ICML (2), pages 217-225, 2013.","title":"Learning and selecting features jointly with point-wise gated boltzmann machines","authors":"Sohn","year":"2013","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wan et al., 2015] Cheng Wan, Xiaoming Jin, Guiguang Ding, and Dou Shen. Gaussian cardinality restricted boltz- mann machines. In AAAI, 2015.","title":"Gaussian cardinality restricted boltzmann machines","authors":"Xiaoming Cheng Wan, Guiguang Jin, Dou Ding, Shen","year":"2015","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wang and Ji, 2016] Xiaoyang Wang and Qiang Ji. Object recognition with hidden attributes. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, pages 3498-3504. AAAI Press, 2016.","title":"Object recognition with hidden attributes","authors":"Xiaoyang Wang, Qiang Ji","year":"2016","venue":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2016/494"},{"position":25,"raw":"[Wang and Mori, 2010] Yang Wang and Greg Mori. A dis- criminative latent model of object classes and attributes. Computer Vision-ECCV 2010, pages 155-168, 2010.","title":"A discriminative latent model of object classes and attributes","authors":"Yang Wang, Greg Mori","year":"2010","venue":"Computer Vision-ECCV 2010","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Wei and Pal, 2011] Bin Wei and Christopher J Pal. Hetero- geneous transfer learning with rbms. In AAAI, 2011.","title":"Heterogeneous transfer learning with rbms","authors":"Pal ; ] Bin Wei, Christopher J Wei, Pal","year":"2011","venue":"AAAI","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}