{"type":"ScholarlyArticle","title":"Ordinal Zero-Shot Learning","authors":[{"name":"Zengwei Huo","slug":"zengwei-huo","given":"Zengwei","family":"Huo","affiliation":"MOE Key Laboratory of Computer Network and Information Integration , School of Computer Science and Engineering , Southeast University , Nanjing 210096 , China"},{"name":"Xin Geng","slug":"xin-geng","given":"Xin","family":"Geng","affiliation":"MOE Key Laboratory of Computer Network and Information Integration , School of Computer Science and Engineering , Southeast University , Nanjing 210096 , China"}],"abstract":"Zero-shot learning predicts new class even if no training data is available for that class. The solution to conventional zero-shot learning usually depends on side information such as attribute or text corpora. But these side information is not easy to obtain or use. Fortunately in many classification tasks, the class labels are ordered, and therefore closely related to each other. This paper deals with zero-shot learning for ordinal classification. The key idea is using label relevance to expand supervision information from seen labels to unseen labels. The proposed method SIDL generates a supervision intensity distribution (SID) that contains each label's supervision intensity, and then learns a mapping from instance to SID. Experiments on two typical ordinal classification problems, i.e., head pose estimation and age estimation, show that SIDL performs significantly better than the compared regression methods. Furthermore, SIDL appears much more robust against the increase of unseen labels than other compared baselines.","doi":"10.24963/ijcai.2017/266","url":"https://ijcai.org/proceedings/2017/266","pdf":"https://ijcai.org/proceedings/2017/0266.pdf","markdown":"https://ijcai.org/proceedings/2017/266.md","bibtex":"https://ijcai.org/proceedings/2017/bibtex/266","volume":{"slug":"2017","title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2017","url":"https://ijcai.org/proceedings/2017/","year":2017,"location":"Melbourne, Australia","dates":"19-25 August 2017","editors":"Carles Sierra","isbn":"978-0-9992411-0-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2017"},"section":"Machine Learning A-R","track":"Main track","number":266,"pages":{"first":1916,"last":1922},"keywords":["Machine Learning: Classification","Machine Learning: Machine Learning"],"videos":[],"references":[{"position":1,"raw":"[Akata et al., 2013] Zeynep Akata, Florent Perronnin, Zaid Har- chaoui, and Cordelia Schmid. Label-embedding for attribute- based classification. In in Proc. IEEE Intl Conf. on Computer Vision and Pattern Recognition, Portland, Oregon, USA, June 2013.","title":"Label-embedding for attributebased classification","authors":"Zeynep Akata, Florent Perronnin, Zaid Harchaoui, Cordelia Schmid","year":"2013","venue":"Proc. IEEE Intl Conf. on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Baocai et al., 2009] Yin Baocai, Sun Yanfeng, Wang Chengzhang, and Ge Yun. Bjut-3d large scale 3d face database and information processing. Journal of Computer Research and Development, 6:020, 2009.","title":"Bjut-3d large scale 3d face database and information processing","authors":"Yin Baocai, Sun Yanfeng, Wang Chengzhang, Ge Yun","year":"2009","venue":"Journal of Computer Research and Development","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Berg et al., 2010] Tamara L Berg, Alexander C Berg, and Jonathan Shih. Automatic attribute discovery and characterization from noisy web data. In in Proc. European Conf. Computer Vision, pages 663-676, Crete, Greece, 2010. Springer.","title":"Automatic attribute discovery and characterization from noisy web data","authors":"Tamara L Berg, Alexander C Berg, Jonathan Shih","year":"2010","venue":"Proc. European Conf. Computer Vision","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Branson et al., 2010] Steve Branson, Catherine Wah, Florian Schroff, Boris Babenko, Peter Welinder, Pietro Perona, and Serge Belongie. Visual recognition with humans in the loop. In in Proc. European Conf. Computer Vision, pages 438-451, Crete, Greece, 2010. Springer.","title":"Visual recognition with humans in the loop","authors":"Steve Branson, Catherine Wah, Florian Schroff, Boris Babenko, Peter Welinder, Pietro Perona, Serge Belongie","year":"2010","venue":"Proc. European Conf. Computer Vision","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chang and Lin, 2011] Chih-Chung Chang and Chih-Jen Lin. LIB- SVM: A library for support vector machines. ACM Trans. on Intelligent Systems and Technology, 2:27:1-27:27, 2011.","title":"LIB-SVM: A library for support vector machines","authors":"Chang, Lin ; ] Chih-Chung Chang, Chih-Jen Lin","year":"2011","venue":"ACM Trans. on Intelligent Systems and Technology","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chang et al., 2011] Kuang-Yu Chang, Chu-Song Chen, and Yi- Ping Hung. Ordinal hyperplanes ranker with cost sensitivities for age estimation. In in Proc. IEEE Intl Conf. on Computer Vi- sion and Pattern Recognition, pages 585-592, Colorado Springs, CO, 2011.","title":"Ordinal hyperplanes ranker with cost sensitivities for age estimation","authors":"Kuang-Yu Chang, Chu-Song Chen, Yi-Ping Hung","year":"2011","venue":"Proc. IEEE Intl Conf. on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Elhoseiny et al., 2013] Mohamed Elhoseiny, Babak Saleh, and Ahmed Elgammal. Write a classifier: Zero-shot learning using purely textual descriptions. In in Proc. Intl Conf. Computer Vi- sion, Sydney, Australia, 2013.","title":"Write a classifier: Zero-shot learning using purely textual descriptions","authors":"Mohamed Elhoseiny, Babak Saleh, Ahmed Elgammal","year":"2013","venue":"Proc. Intl Conf. Computer Vision","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 in Proc. IEEE Intl Conf. on Computer Vision and Pattern Recognition, pages 1778-1785, Miami, Florida, USA, 2009. IEEE.","title":"Describing objects by their attributes","authors":"Ali Farhadi, Ian Endres, Derek Hoiem, David Forsyth","year":"2009","venue":"Proc. IEEE Intl Conf. on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Geng and Xia, 2014] Xin Geng and Yu Xia. Head pose estimation based on multivariate label distribution. In in Proc. IEEE Intl Conf. on Computer Vision and Pattern Recognition, pages 1837- 1842, Columbus, OH, USA, 2014.","title":"Head pose estimation based on multivariate label distribution","authors":"Xin Geng, Yu Xia","year":"2014","venue":"Proc. IEEE Intl Conf. on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Geng et al., 2013] Xin Geng, Chao Yin, and Zhi-Hua Zhou. Facial age estimation by learning from label distributions. IEEE Trans. on Pattern Analysis and Machine Intelligence, 35(10):2401- 2412, 2013.","title":"Facial age estimation by learning from label distributions","authors":"Xin Geng, Zhi-Hua Chao Yin, Zhou","year":"2013","venue":"IEEE Trans. on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Geng, 2016] Xin Geng. Label distribution learning. IEEE Trans. on Knowledge and Data Engineering, 28(7):1734-1748, 2016.","title":"Label distribution learning","authors":"Xin Geng","year":"2016","venue":"IEEE Trans. on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Gourier et al., 2004] Nicolas Gourier, Daniela Hall, and James L. Crowley. Estimating face orientation from robust detection of salient facial features. In Proc. Pointing 2004, ICPR, Int'l Work- shop on Visual Observation of Deictic Gestures, Cambridge, UK, 2004.","title":"Estimating face orientation from robust detection of salient facial features","authors":"Nicolas Gourier, Daniela Hall, James L Crowley","year":"2004","venue":"Proc. Pointing 2004, ICPR, Int'l Workshop on Visual Observation of Deictic Gestures","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Guo and Mu, 2011] Guodong Guo and Guowang Mu. Simultane- ous dimensionality reduction and human age estimation via ker- nel partial least squares regression. In in Proc. IEEE Intl Conf. on Computer Vision and Pattern Recognition, pages 657-664, Col- orado Springs, CO, 2011.","title":"Simultaneous dimensionality reduction and human age estimation via kernel partial least squares regression","authors":"Mu Guo, Guodong Guo, Guowang Mu","year":"2011","venue":"Proc. IEEE Intl Conf. on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Guo et al., 2008] Guodong Guo, Yun Fu, Charles R. Dyer, and Thomas S. Huang. Head pose estimation: Classification or re- gression? In in Proc. Int'l Conf. Pattern Recognition, pages 1-4, Tampa, FL, 2008.","title":"Head pose estimation: Classification or regression?","authors":"Guodong Guo, Yun Fu, Charles R Dyer, Thomas S Huang","year":"2008","venue":"Proc. Int'l Conf. Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Guo et al., 2009] Guodong Guo, Guowang Mu, Yun Fu, and Thomas S. Huang. Human age estimation using bio-inspired fea- tures. In in Proc. IEEE Intl Conf. on Computer Vision and Pattern Recognition, pages 112-119, Miami, FL, 2009.","title":"Human age estimation using bio-inspired features","authors":"Guodong Guo, Guowang Mu, Yun Fu, Thomas S Huang","year":"2009","venue":"Proc. IEEE Intl Conf. on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Haj et al., 2012] Murad Al Haj, Jordi Gonzàlez, and Larry S. Davis. On partial least squares in head pose estimation: How to simultaneously deal with misalignment. In in Proc. IEEE Intl Conf. on Computer Vision and Pattern Recognition, pages 2602- 2609, Providence, RI, 2012.","title":"On partial least squares in head pose estimation: How to simultaneously deal with misalignment","authors":"Murad Al Haj, Jordi Gonzàlez, Larry S Davis","year":"2012","venue":"Proc. IEEE Intl Conf. on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Lampert et al., 2014] Christoph H Lampert, Hannes Nickisch, and Stefan Harmeling. Attribute-based classification for zero-shot vi- sual object categorization. IEEE Trans. on Pattern Analysis and Machine Intelligence, 36(3):453-465, 2014.","title":"Attribute-based classification for zero-shot visual object categorization","authors":"Hannes Christoph H Lampert, Stefan Nickisch, Harmeling","year":"2014","venue":"IEEE Trans. on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Lanitis et al., 2002] Andreas Lanitis, Christopher J. Taylor, and Timothy F. Cootes. Toward automatic simulation of aging effects on face images. IEEE Trans. on Pattern Analysis and Machine Intelligence, 24(4):442-455, 2002.","title":"Toward automatic simulation of aging effects on face images","authors":"Andreas Lanitis, Christopher J Taylor, Timothy F Cootes","year":"2002","venue":"IEEE Trans. on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Lanitis et al., 2004] Andreas Lanitis, Chrisina Draganova, and Chris Christodoulou. Comparing different classifiers for auto- matic age estimation. IEEE Trans. on Systems, Man, and Cyber- netics, Part B (Cybernetics), 34(1):621-628, 2004.","title":"Comparing different classifiers for automatic age estimation","authors":"Lanitis","year":"2004","venue":"IEEE Trans. on Systems, Man, and Cybernetics, Part B (Cybernetics)","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Liu and Nocedal, 1989] Dong C. Liu and Jorge Nocedal. On the limited memory BFGS method for large scale optimization. Mathematical Programming, 45(3):503-528, 1989.","title":"On the limited memory BFGS method for large scale optimization","authors":"Dong C Liu, Jorge Nocedal","year":"1989","venue":"Mathematical Programming","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Palatucci et al., 2009] Mark Palatucci, Dean Pomerleau, Geof- frey E. Hinton, and Tom M. Mitchell. Zero-shot learning with semantic output codes. In in Proc. Advances in Neural Informa- tion Processing Systems, pages 1410-1418, Vancouver,Canada, 2009.","title":"Zero-shot learning with semantic output codes","authors":"Mark Palatucci, Dean Pomerleau, Geoffrey E Hinton, Tom M Mitchell","year":"2009","venue":"Proc. Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"Curran Associates, Inc. [Parikh and Grauman, 2011] Devi Parikh and Kristen Grauman. In- teractively building a discriminative vocabulary of nameable at- tributes. In in Proc. IEEE Intl Conf. on Computer Vision and Pattern Recognition, pages 1681-1688, Colorado Springs, CO, 2011. IEEE.","title":"Interactively building a discriminative vocabulary of nameable attributes","authors":"Inc [ Curran Associates, Grauman Parikh, Devi Parikh, Kristen Grauman","year":"2011","venue":"Proc. IEEE Intl Conf. on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Ricanek and Tamirat, 2006] Karl Ricanek and Tesafaye Tamirat. Morph: A longitudinal image database of normal adult age- progression. In in Proc. Int'l Conf. Automatic Face and Gesture Recognition, pages 341-345, Southampton, UK, 2006.","title":"Karl Ricanek and Tesafaye Tamirat. Morph: A longitudinal image database of normal adult ageprogression","authors":"Tamirat Ricanek","year":"2006","venue":"Proc. Int'l Conf. Automatic Face and Gesture Recognition","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Rohrbach et al., 2010] Marcus Rohrbach, Michael Stark, György Szarvas, Iryna Gurevych, and Bernt Schiele. What helps where- and why? semantic relatedness for knowledge transfer. In in Proc. IEEE Intl Conf. on Computer Vision and Pattern Recog- nition, pages 910-917, San Francisco, California, USA, 2010. IEEE. Socher et al., 2013]","title":"What helps whereand why? semantic relatedness for knowledge transfer","authors":"Rohrbach","year":"2010","venue":"Proc. IEEE Intl Conf. on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"Richard Socher, Milind Ganjoo, Christo- pher D Manning, and Andrew Ng. Zero-shot learning through cross-modal transfer. In in Proc. Advances in Neural Information Processing Systems, pages 935-943, South Lake Tahoe, Nevada, US, 2013.","title":"Zero-shot learning through cross-modal transfer","authors":"Richard Socher, Milind Ganjoo, Christopher D Manning, Andrew Ng","year":"2013","venue":"Proc. Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Yan et al., 2007] Shuicheng Yan, Dong Xu, Benyu Zhang, HongJiang Zhang, Qiang Yang, and Stephen Lin. Graph em- bedding and extensions: A general framework for dimensionality reduction. IEEE Trans. on Pattern Analysis and Machine Intelli- gence, 29(1):40-51, 2007.","title":"Graph embedding and extensions: A general framework for dimensionality reduction","authors":"Shuicheng Yan, Dong Xu, Benyu Zhang, Hongjiang Zhang, Qiang Yang, Stephen Lin","year":"2007","venue":"IEEE Trans. on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zhang and Saligrama, 2016] Ziming Zhang and Venkatesh Saligrama. Zero-shot learning via joint latent similarity em- bedding. In in Proc. IEEE Intl Conf. on Computer Vision and Pattern Recognition, Las Vegas, Nevada,USA, June 2016.","title":"Zero-shot learning via joint latent similarity embedding","authors":"Ziming Zhang, Venkatesh Saligrama","year":"2016","venue":"Proc. IEEE Intl Conf. on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}