{"type":"ScholarlyArticle","title":"Asymmetric Distribution Measure for Few-shot Learning","authors":[{"name":"Wenbin Li","slug":"wenbin-li","given":"Wenbin","family":"Li","affiliation":"National Key Laboratory for Novel Software Technology , Nanjing University , China"},{"name":"Lei Wang","slug":"lei-wang","given":"Lei","family":"Wang","affiliation":"University of Wollongong , Australia"},{"name":"Jing Huo","slug":"jing-huo","given":"Jing","family":"Huo","affiliation":"National Key Laboratory for Novel Software Technology , Nanjing University , China"},{"name":"Yinghuan Shi","slug":"yinghuan-shi","given":"Yinghuan","family":"Shi","affiliation":"National Key Laboratory for Novel Software Technology , Nanjing University , China"},{"name":"Yang Gao","slug":"yang-gao","given":"Yang","family":"Gao","affiliation":"National Key Laboratory for Novel Software Technology , Nanjing University , China"},{"name":"Jiebo Luo","slug":"jiebo-luo","given":"Jiebo","family":"Luo","affiliation":"University of Rochester , USA"}],"abstract":"The core idea of metric-based few-shot image classification is to directly measure the relations between query images and support classes to learn transferable feature embeddings. Previous work mainly focuses on image-level feature representations, which actually cannot effectively estimate a class's distribution due to the scarcity of samples. Some recent work shows that local descriptor based representations can achieve richer representations than image-level based representations. However, such works are still based on a less effective instance-level metric, especially a symmetric metric, to measure the relation between a query image and a support class. Given the natural asymmetric relation between a query image and a support class, we argue that an asymmetric measure is more suitable for metric-based few-shot learning. To that end, we propose a novel Asymmetric Distribution Measure (ADM) network for few-shot learning by calculating a joint local and global asymmetric measure between two multivariate local distributions of a query and a class. Moreover, a task-aware Contrastive Measure Strategy (CMS) is proposed to further enhance the measure function. On popular miniImageNet and tieredImageNet, ADM can achieve the state-of-the-art results, validating our innovative design of asymmetric distribution measures for few-shot learning. The source code can be downloaded from https://github.com/WenbinLee/ADM.git.","doi":"10.24963/ijcai.2020/409","url":"https://ijcai.org/proceedings/2020/409","pdf":"https://ijcai.org/proceedings/2020/0409.pdf","markdown":"https://ijcai.org/proceedings/2020/409.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/409","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Machine Learning","track":"Main track","number":409,"pages":{"first":2957,"last":2963},"keywords":["Machine Learning: Transfer, Adaptation, Multi-task Learning","Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24517/file_24517.m3u8","length_sec":259,"provider":"hls"}],"references":[{"position":1,"raw":"[Allen et al., 2019] Kelsey R Allen, Evan Shelhamer, Hanul Shin, and Joshua B Tenenbaum. Infinite mixture proto- types for few-shot learning. ICML, 2019.","title":"Infinite mixture prototypes for few-shot learning","authors":"Evan Kelsey R Allen, Hanul Shelhamer, Joshua B Shin, Tenenbaum","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Antoniou et al., 2017] Antreas Antoniou, Amos Storkey, and Harrison Edwards. Data augmentation generative ad- versarial networks. arXiv, 2017.","title":"Data augmentation generative adversarial networks","authors":"Antreas Antoniou, Amos Storkey, Harrison Edwards","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Berthelot et al., 2017] David Berthelot, Thomas Schumm, and Luke Metz. Began: Boundary equilibrium generative adversarial networks. arXiv, 2017.","title":"Began: Boundary equilibrium generative adversarial networks","authors":"David Berthelot, Thomas Schumm, Luke Metz","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Deng et al., 2009] Jia Deng, Wei Dong, Richard Socher, Li- Jia Li, Kai Li, and Li Fei-Fei. Imagenet: A large-scale hierarchical image database. In CVPR, pages 248-255, 2009.","title":"Imagenet: A large-scale hierarchical image database","authors":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Li Fei-Fei","year":"2009","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Duchi, 2007] John Duchi. Derivations for linear algebra and optimization. Berkeley, California, 3, 2007.","title":"Derivations for linear algebra and optimization","authors":"John Duchi","year":"2007","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Finn et al., 2017] Chelsea Finn, Pieter Abbeel, and Sergey Levine. Model-agnostic meta-learning for fast adaptation of deep networks. In ICML, pages 1126-1135, 2017.","title":"Model-agnostic meta-learning for fast adaptation of deep networks","authors":"Finn","year":"2017","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[He et al., 2018] Ran He, Xiang Wu, Zhenan Sun, and Tieniu Tan. Wasserstein cnn: Learning invariant features for nir- vis face recognition. IEEE Transactions on Pattern Anal- ysis and Machine Intelligence, 2018.","title":"Wasserstein cnn: Learning invariant features for nirvis face recognition","authors":"Ran He, Xiang Wu, Zhenan Sun, Tieniu Tan","year":"2018","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Jamal and Qi, 2019] Muhammad Abdullah Jamal and Guo- Jun Qi. Task agnostic meta-learning for few-shot learning. In CVPR, pages 11719-11727, 2019.","title":"Muhammad Abdullah Jamal and Guo-Jun Qi. Task agnostic meta-learning for few-shot learning","authors":"Qi Jamal","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kingma and Ba, 2014] Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv, 2014.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Koch et al., 2015] Gregory Koch, Richard Zemel, and Rus- lan Salakhutdinov. Siamese neural networks for one-shot image recognition. In ICML deep learning workshop, vol- ume 2, 2015.","title":"Siamese neural networks for one-shot image recognition","authors":"Gregory Koch, Richard Zemel, Ruslan Salakhutdinov","year":"2015","venue":"ICML deep learning workshop","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Lee et al., 2019] Kwonjoon Lee, Subhransu Maji, Avinash Ravichandran, and Stefano Soatto. Meta-learning with dif- ferentiable convex optimization. In CVPR, pages 10657- 10665, 2019.","title":"Meta-learning with differentiable convex optimization","authors":"Lee","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Li et al., 2019a] Wenbin Li, Lei Wang, Jinglin Xu, Jing Huo, Gao Yang, and Jiebo Luo. Revisiting local descrip- tor based image-to-class measure for few-shot learning. In CVPR, 2019.","title":"Revisiting local descriptor based image-to-class measure for few-shot learning","authors":"Li","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Li et al., 2019b] Wenbin Li, Jinglin Xu, Jing Huo, Lei Wang, Gao Yang, and Jiebo Luo. Distribution consistency based covariance metric networks for few-shot learning. In AAAI, 2019.","title":"Distribution consistency based covariance metric networks for few-shot learning","authors":"Li","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Mishra et al., 2017] Nikhil Mishra, Mostafa Rohaninejad, Xi Chen, and Pieter Abbeel. A simple neural attentive meta-learner. arXiv, 2017.","title":"A simple neural attentive meta-learner","authors":"Nikhil Mishra, Mostafa Rohaninejad, Xi Chen, Pieter Abbeel","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Olkin and Pukelsheim, 1982] Ingram Olkin and Friedrich Pukelsheim. The distance between two random vectors with given dispersion matrices. Linear Algebra and its Applications, 48:257-263, 1982.","title":"The distance between two random vectors with given dispersion matrices","authors":"Ingram Olkin, Friedrich Pukelsheim","year":"1982","venue":"Linear Algebra and its Applications","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Ravi and Larochelle, 2017] Sachin Ravi and Hugo Larochelle. Optimization as a model for few-shot learning. 2017.","title":"Optimization as a model for few-shot learning","authors":"Larochelle ; Ravi, Sachin Ravi, Hugo Larochelle","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Ren et al., 2018] Mengye Ren, Eleni Triantafillou, Sachin Ravi, Jake Snell, Kevin Swersky, Joshua B Tenenbaum, Hugo Larochelle, and Richard S Zemel. Meta-learning for semi-supervised few-shot classification. arXiv, 2018.","title":"Meta-learning for semi-supervised few-shot classification","authors":"Ren","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Schwartz et al., 2018] Eli Schwartz, Leonid Karlinsky, Joseph Shtok, Sivan Harary, Mattias Marder, Abhishek Kumar, Rogerio Feris, Raja Giryes, and Alex Bronstein. Delta-encoder: an effective sample synthesis method for few-shot object recognition. In NeurIPS, pages 2850- 2860, 2018.","title":"Delta-encoder: an effective sample synthesis method for few-shot object recognition","authors":"Eli Schwartz, Leonid Karlinsky, Joseph Shtok, Sivan Harary, Mattias Marder, Abhishek Kumar, Rogerio Feris, Raja Giryes, Alex Bronstein","year":"2018","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Snell et al., 2017] Jake Snell, Kevin Swersky, Richard Zemel, and Richard Zemel. Prototypical networks for few- shot learning. In NeurIPS, pages 4077-4087, 2017.","title":"Prototypical networks for fewshot learning","authors":"Jake Snell, Kevin Swersky, Richard Zemel, Richard Zemel","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Sun et al., 2019] Qianru Sun, Yaoyao Liu, Tat-Seng Chua, and Bernt Schiele. Meta-transfer learning for few-shot learning. In CVPR, pages 403-412, 2019.","title":"Meta-transfer learning for few-shot learning","authors":"Sun","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Sung et al., 2018] Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang, Philip HS Torr, and Timothy M Hospedales. Learning to compare: Relation network for few-shot learn- ing. In CVPR, pages 1199-1208, 2018.","title":"Learning to compare: Relation network for few-shot learning","authors":"Sung","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Vinyals et al., 2016] Oriol Vinyals, Charles Blundell, Timo- thy Lillicrap, Daan Wierstra, et al. Matching networks for one shot learning. In NeurIPS, pages 3630-3638, 2016.","title":"Matching networks for one shot learning","authors":"Oriol Vinyals, Charles Blundell, Timothy Lillicrap, Daan Wierstra","year":"2016","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Xian et al., 2019] Yongqin Xian, Saurabh Sharma, Bernt Schiele, and Zeynep Akata. f-vaegan-d2: A feature gen- erating framework for any-shot learning. In CVPR, pages 10275-10284, 2019.","title":"f-vaegan-d2: A feature generating framework for any-shot learning","authors":"Xian","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}