{"type":"ScholarlyArticle","title":"Quality-agnostic Image Captioning to Safely Assist People with Vision Impairment","authors":[{"name":"Lu Yu","slug":"lu-yu","given":"Lu","family":"Yu","affiliation":"Tianjin University of Technology , Tian jin , China"},{"name":"Malvina Nikandrou","slug":"malvina-nikandrou","given":"Malvina","family":"Nikandrou","affiliation":"Heriot-Watt University , Edinburgh , United Kingdom"},{"name":"Jiali Jin","slug":"jiali-jin","given":"Jiali","family":"Jin","affiliation":"Tianjin University of Technology , Tian jin , China"},{"name":"Verena Rieser","slug":"verena-rieser","given":"Verena","family":"Rieser","affiliation":"Heriot-Watt University , Edinburgh , United Kingdom; Alana AI"}],"abstract":"Automated image captioning has the potential to be a useful tool for people with vision impairments. Images taken by this user group are often noisy,  which leads to incorrect and even unsafe model predictions. In this paper, we propose a quality-agnostic framework to improve the performance and robustness of image captioning models for visually impaired people. We address this problem from three angles: data, model, and evaluation. First, we show how data augmentation techniques for generating synthetic noise can address data sparsity in this domain. Second, we enhance the robustness of the model by expanding a state-of-the-art model to a dual network architecture, using the augmented data and leveraging different consistency losses. Our results demonstrate increased performance, e.g. an absolute improvement of 2.15 on CIDEr, compared to state-of-the-art image captioning networks, as well as increased robustness to noise with up to 3 points improvement on CIDEr in more noisy settings. Finally, we evaluate the prediction reliability using confidence calibration on images with different difficulty / noise levels, showing that our models perform more reliably\r\nin safety-critical situations. The improved model is part of an assisted living application, which we develop in partnership with the Royal National Institute of Blind People.","doi":"10.24963/ijcai.2023/697","url":"https://ijcai.org/proceedings/2023/697","pdf":"https://ijcai.org/proceedings/2023/0697.pdf","markdown":"https://ijcai.org/proceedings/2023/697.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/697","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"AI for Good","track":"AI for Good","number":697,"pages":{"first":6281,"last":6289},"keywords":["AI for Good: Humans and AI","AI for Good: Uncertainty in AI"],"videos":[],"references":[{"position":1,"raw":"[Abuduweili et al., 2021] Abulikemu Abuduweili, Xingjian Li, Humphrey Shi, Cheng-Zhong Xu, and Dejing Dou. Adaptive consistency regularization for semi-supervised transfer learning. In Proceedings of the IEEE/CVF Confer- ence on Computer Vision and Pattern Recognition, pages 6923-6932, 2021.","title":"Adaptive consistency regularization for semi-supervised transfer learning","authors":"Abuduweili","year":"2021","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Anderson et al., 2016] Peter Anderson, Basura Fernando, Mark Johnson, and Stephen Gould. Spice: Semantic propositional image caption evaluation. In European con- ference on computer vision, pages 382-398. Springer, 2016.","title":"Spice: Semantic propositional image caption evaluation","authors":"Anderson","year":"2016","venue":"European conference on computer vision","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bennett et al., 2018] Cynthia L. Bennett, Jane E, Martez E. Mott, Edward Cutrell, and Meredith Ringel Morris. How Teens with Visual Impairments Take, Edit, and Share Pho- tos on Social Media, page 1-12. Association for Comput- ing Machinery, New York, NY, USA, 2018.","title":"How Teens with Visual Impairments Take, Edit, and Share Photos on Social Media","authors":"Cynthia L Bennett, Jane E, Martez E Mott, Edward Cutrell, Meredith Ringel, Morris","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bhattacharya et al., 2019] Nilavra Bhattacharya, Qing Li, and Danna Gurari. Why does a visual question have dif- ferent answers? In Proceedings of the IEEE/CVF Interna- tional Conference on Computer Vision, pages 4271-4280, 2019.","title":"Why does a visual question have different answers","authors":"Bhattacharya","year":"2019","venue":"Proceedings of the IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Bigham et al., 2010] Jeffrey P Bigham, Chandrika Jayant, Hanjie Ji, Greg Little, Andrew Miller, Robert C Miller, Robin Miller, Aubrey Tatarowicz, Brandyn White, Samual White, et al. Vizwiz: nearly real-time answers to visual questions. In Proceedings of the 23nd annual ACM sym- posium on User interface software and technology, pages 333-342, 2010.","title":"Vizwiz: nearly real-time answers to visual questions","authors":"Chandrika Jeffrey P Bigham, Hanjie Jayant, Greg Ji, Andrew Little, Robert C Miller, Robin Miller, Aubrey Miller, Brandyn Tatarowicz, Samual White, White","year":"2010","venue":"Proceedings of the 23nd annual ACM symposium on User interface software and technology","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chen et al., 2022] Chongyan Chen, Samreen Anjum, and Danna Gurari. Grounding answers for visual questions asked by visually impaired people. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 19098-19107, 2022.","title":"Grounding answers for visual questions asked by visually impaired people","authors":"Chen","year":"2022","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Chiu et al., 2020a] T. Chiu, Y. Zhao, and D. Gurari. As- sessing image quality issues for real-world problems. In 2020 IEEE/CVF Conference on Computer Vision and Pat- tern Recognition (CVPR), pages 3643-3653, Los Alami- tos, CA, USA, jun 2020. IEEE Computer Society.","title":"Assessing image quality issues for real-world problems","authors":"Chiu","year":"2020","venue":"IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Chiu et al., 2020b] Tai-Yin Chiu, Yinan Zhao, and Danna Gurari. Assessing image quality issues for real-world problems. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3646- 3656, 2020.","title":"Assessing image quality issues for real-world problems","authors":"Chiu","year":"2020","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Davis et al., 2020] Nathan Davis, Bo Xie, and Danna Gu- rari. Quality of images showing medication packaging from individuals with vision impairments: Implications for the design of visual question answering applications. Proceedings of the Association for Information Science and Technology, 57, 10 2020.","title":"Quality of images showing medication packaging from individuals with vision impairments: Implications for the design of visual question answering applications","authors":"Nathan Davis, Bo Xie, Danna Gurari","year":"2020","venue":"Proceedings of the Association for Information Science and Technology","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Denkowski and Lavie, 2014] Michael Denkowski and Alon Lavie. Meteor universal: Language specific translation evaluation for any target language. In Proceedings of the ninth workshop on statistical machine translation, pages 376-380, 2014.","title":"Meteor universal: Language specific translation evaluation for any target language","authors":"Lavie Denkowski, Michael Denkowski, Alon Lavie","year":"2014","venue":"Proceedings of the ninth workshop on statistical machine translation","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Dinan et al., 2021] Emily Dinan, Gavin Abercrombie, A Stevie Bergman, Shannon Spruit, Dirk Hovy, Y-Lan Boureau, and Verena Rieser. Anticipating safety issues in e2e conversational ai: Framework and tooling. arXiv preprint arXiv:2107.03451, 2021.","title":"Anticipating safety issues in e2e conversational ai: Framework and tooling","authors":"Emily Dinan, Gavin Abercrombie, Stevie Bergman, Shannon Spruit, Dirk Hovy, Y-Lan Boureau, Verena Rieser","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Friedman et al., 2017] Batya Friedman, David G Hendry, and Alan Borning. A survey of value sensitive design methods. Foundations and Trends in Human-Computer Interaction, 11(2):63-125, 2017.","title":"A survey of value sensitive design methods","authors":"Batya Friedman, David G Hendry, Alan Borning","year":"2017","venue":"Foundations and Trends in Human-Computer Interaction","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Gkatzia et al., 2016] Dimitra Gkatzia, Oliver Lemon, and Verena Rieser. Natural language generation enhances hu- man decision-making with uncertain information. In 54th Annual Meeting of the Association for Computational Lin- guistics 2016, pages 264-268. Association for Computa- tional Linguistics, 2016.","title":"Natural language generation enhances human decision-making with uncertain information","authors":"Dimitra Gkatzia, Oliver Lemon, Verena Rieser","year":"2016","venue":"54th Annual Meeting of the Association for Computational Linguistics 2016","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Gong et al., 2021] Chengyue Gong, Dilin Wang, and Qiang Liu. Alphamatch: Improving consistency for semi- supervised learning with alpha-divergence. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pat- tern Recognition, pages 13683-13692, 2021.","title":"Alphamatch: Improving consistency for semisupervised learning with alpha-divergence","authors":"Gong","year":"2021","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Guo et al., 2017] Chuan Guo, Geoff Pleiss, Yu Sun, and Kilian Q Weinberger. On calibration of modern neural net- works. In International Conference on Machine Learning, pages 1321-1330. PMLR, 2017.","title":"On calibration of modern neural networks","authors":"Chuan Guo, Geoff Pleiss, Yu Sun, Kilian Q Weinberger","year":"2017","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Gurari et al., 2020] Danna Gurari, Yinan Zhao, Meng Zhang, and Nilavra Bhattacharya. Captioning images taken by people who are blind. In European Conference on Computer Vision, pages 417-434. Springer, 2020.","title":"Captioning images taken by people who are blind","authors":"Danna Gurari, Yinan Zhao, Meng Zhang, Nilavra Bhattacharya","year":"2020","venue":"European Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Han et al., 2021] Xiaotian Han, Jianwei Yang, Houdong Hu, Lei Zhang, Jianfeng Gao, and Pengchuan Zhang. Image scene graph generation (sgg) benchmark. arXiv preprint arXiv:2107.12604, 2021.","title":"Image scene graph generation (sgg) benchmark","authors":"Xiaotian Han, Jianwei Yang, Houdong Hu, Lei Zhang, Jianfeng Gao, Pengchuan Zhang","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[He et al., 2019] Kaiming He, Ross Girshick, and Piotr Dollár. Rethinking imagenet pre-training. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 4918-4927, 2019.","title":"Rethinking imagenet pre-training","authors":"He","year":"2019","venue":"Proceedings of the IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Hu et al., 2021] Zijian Hu, Zhengyu Yang, Xuefeng Hu, and Ram Nevatia. Simple: Similar pseudo label exploita- tion for semi-supervised classification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pat- tern Recognition, pages 15099-15108, 2021.","title":"Simple: Similar pseudo label exploitation for semi-supervised classification","authors":"Zijian Hu, Zhengyu Yang, Xuefeng Hu, Ram Nevatia","year":"2021","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Huang et al., 2019] Lun Huang, Wenmin Wang, Jie Chen, and Xiao-Yong Wei. Attention on attention for image cap- tioning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 4634-4643, 2019.","title":"Attention on attention for image captioning","authors":"Lun Huang, Wenmin Wang, Jie Chen, Xiao-Yong Wei","year":"2019","venue":"Proceedings of the IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Isobe et al., 2021] Takashi Isobe, Xu Jia, Shuaijun Chen, Jianzhong He, Yongjie Shi, Jianzhuang Liu, Huchuan Lu, and Shengjin Wang. Multi-target domain adaptation with collaborative consistency learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8187-8196, 2021.","title":"Multi-target domain adaptation with collaborative consistency learning","authors":"Takashi Isobe, Xu Jia, Shuaijun Chen, Jianzhong He, Yongjie Shi, Jianzhuang Liu, Huchuan Lu, Shengjin Wang","year":"2021","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Lai et al., 2021] Xin Lai, Zhuotao Tian, Li Jiang, Shu Liu, Hengshuang Zhao, Liwei Wang, and Jiaya Jia. Semi-supervised semantic segmentation with directional context-aware consistency. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1205-1214, 2021.","title":"Semi-supervised semantic segmentation with directional context-aware consistency","authors":"Xin Lai, Zhuotao Tian, Li Jiang, Shu Liu, Hengshuang Zhao, Liwei Wang, Jiaya Jia","year":"2021","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Lin et al., 2014] Tsung-Yi Lin, Michael Maire, Serge Be- longie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick. Microsoft coco: Com- mon objects in context. In European conference on com- puter vision, pages 740-755. Springer, 2014.","title":"Microsoft coco: Common objects in context","authors":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, C Lawrence, Zitnick","year":"2014","venue":"European conference on computer vision","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Lin, 2004] Chin-Yew Lin. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out, pages 74-81, 2004.","title":"Rouge: A package for automatic evaluation of summaries","authors":"Chin-Yew Lin","year":"2004","venue":"Text summarization branches out","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[MacLeod et al., 2017] Haley MacLeod, Cynthia L. Bennett, Meredith Ringel Morris, and Edward Cutrell. Understand- ing blind people's experiences with computer-generated captions of social media images. In Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems, CHI '17, page 5988-5999, New York, NY, USA, 2017. Association for Computing Machinery.","title":"Understanding blind people's experiences with computer-generated captions of social media images","authors":"Haley Macleod, Cynthia L Bennett, Meredith Ringel Morris, Edward Cutrell","year":"2017","venue":"Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems, CHI '17","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Naeini et al., 2015] Mahdi Pakdaman Naeini, Gregory Cooper, and Milos Hauskrecht. Obtaining well calibrated probabilities using bayesian binning. In Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015.","title":"Mahdi Pakdaman Naeini, Gregory Cooper, and Milos Hauskrecht. Obtaining well calibrated probabilities using bayesian binning","authors":"Naeini","year":"2015","venue":"Twenty-Ninth AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Pantazopoulos et al., 2021] George Pantazopoulos, Jeremy Bruyere, Malvina Nikandrou, Thibaud Boissier, Supun Hemanthage, Binha Kumar Sachish, Vidyul Shah, Chris- tian Dondrup, and Oliver Lemon. Vica: Combining visual, social, and task-oriented conversational ai in a healthcare setting. In Proceedings of the 2021 International Confer- ence on Multimodal Interaction, ICMI '21, page 71-79, New York, NY, USA, 2021. Association for Computing Machinery.","title":"Vica: Combining visual, social, and task-oriented conversational ai in a healthcare setting","authors":"George Pantazopoulos, Jeremy Bruyere, Malvina Nikandrou, Thibaud Boissier, Supun Hemanthage, Binha Kumar Sachish, Vidyul Shah, Christian Dondrup, Oliver Lemon","year":"2021","venue":"Proceedings of the 2021 International Conference on Multimodal Interaction, ICMI '21","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Papineni et al., 2002] Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. Bleu: a method for au- tomatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Compu- tational Linguistics, pages 311-318, 2002.","title":"Bleu: a method for automatic evaluation of machine translation","authors":"Kishore Papineni, Salim Roukos, Todd Ward, Wei-Jing Zhu","year":"2002","venue":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Paszke et al., 2017] Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary De- Vito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer. Automatic differentiation in pytorch. In Thirty-first Conference on Neural Information Processing Systems Workshop, 2017.","title":"Automatic differentiation in pytorch","authors":"Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary De-Vito, Zeming Lin, Alban Desmaison, Luca Antiga, Adam Lerer","year":"2017","venue":"Thirty-first Conference on Neural Information Processing Systems Workshop","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Sohn et al., 2020] Kihyuk Sohn, David Berthelot, Nicholas Carlini, Zizhao Zhang, Han Zhang, Colin A Raffel, Ekin Dogus Cubuk, Alexey Kurakin, and Chun-Liang Li. Fixmatch: Simplifying semi-supervised learning with con- sistency and confidence. Advances in Neural Information Processing Systems, 33, 2020.","title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","authors":"Sohn","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Thulasidasan et al., 2019] Sunil Thulasidasan, Gopinath Chennupati, Jeff A Bilmes, Tanmoy Bhattacharya, and Sarah Michalak. On mixup training: Improved calibra- tion and predictive uncertainty for deep neural networks. Advances in Neural Information Processing Systems, 32, 2019.","title":"On mixup training: Improved calibration and predictive uncertainty for deep neural networks","authors":"Gopinath Sunil Thulasidasan, Jeff A Chennupati, Tanmoy Bilmes, Sarah Bhattacharya, Michalak","year":"2019","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Tseng et al., 2022] Yu-Yun Tseng, Alexander Bell, and Danna Gurari. Vizwiz-fewshot: Locating objects in im- ages taken by people with visual impairments. In Eu- ropean Conference on Computer Vision, pages 575-591. Springer, 2022.","title":"Vizwiz-fewshot: Locating objects in images taken by people with visual impairments","authors":"Yu-Yun Tseng, Alexander Bell, Danna Gurari","year":"2022","venue":"European Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Vedantam et al., 2015] Ramakrishna Vedantam, C Lawrence Zitnick, and Devi Parikh. Cider: Consensus- based image description evaluation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4566-4575, 2015.","title":"Cider: Consensusbased image description evaluation","authors":"Ramakrishna Vedantam, Lawrence Zitnick, Devi Parikh","year":"2015","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Wang et al., 2020] Shuo Wang, Zhaopeng Tu, Shuming Shi, and Yang Liu. On the inference calibration of neural ma- chine translation. arXiv preprint arXiv:2005.00963, 2020.","title":"On the inference calibration of neural machine translation","authors":"Shuo Wang, Zhaopeng Tu, Shuming Shi, Yang Liu","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Wu et al., 2019] Ancong Wu, Wei-Shi Zheng, and Jian- Huang Lai. Unsupervised person re-identification by camera-aware similarity consistency learning. In Proceed- ings of the IEEE/CVF International Conference on Com- puter Vision, pages 6922-6931, 2019.","title":"Unsupervised person re-identification by camera-aware similarity consistency learning","authors":"Ancong Wu, Wei-Shi Zheng, Jian-Huang Lai","year":"2019","venue":"Proceedings of the IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Young et al., 2014] Peter Young, Alice Lai, Micah Hodosh, and Julia Hockenmaier. From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions. Transactions of the Association for Computational Linguistics, 2:67-78, 2014.","title":"From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions","authors":"Peter Young, Alice Lai, Micah Hodosh, Julia Hockenmaier","year":"2014","venue":"Transactions of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Zhang et al., 2021] Pengchuan Zhang, Xiujun Li, Xiaowei Hu, Jianwei Yang, Lei Zhang, Lijuan Wang, Yejin Choi, and Jianfeng Gao. Vinvl: Revisiting visual representa- tions in vision-language models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5579-5588, 2021.","title":"Vinvl: Revisiting visual representations in vision-language models","authors":"Zhang","year":"2021","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Zoph et al., 2020] Barret Zoph, Golnaz Ghiasi, Tsung-Yi Lin, Yin Cui, Hanxiao Liu, Ekin Dogus Cubuk, and Quoc Le. Rethinking pre-training and self-training. In Advances in Neural Information Processing Systems, volume 33, pages 3833-3845, 2020.","title":"Rethinking pre-training and self-training","authors":"Barret Zoph, Golnaz Ghiasi, Tsung-Yi Lin, Yin Cui, Hanxiao Liu, Ekin Dogus Cubuk, Quoc Le","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}