{"type":"ScholarlyArticle","title":"Few-shot Classification via Ensemble Learning with Multi-Order Statistics","authors":[{"name":"Sai Yang","slug":"sai-yang","given":"Sai","family":"Yang","affiliation":"School of Electrical Engineering , Nantong University , Nantong , China"},{"name":"Fan Liu","slug":"fan-liu","given":"Fan","family":"Liu","affiliation":"College of Computer and Information , Hohai University , Nanjing , China; Science and Technology on Underwater Vehicle Technology Laboratory , Harbin Engineering University , Harbin , China"},{"name":"Delong Chen","slug":"delong-chen","given":"Delong","family":"Chen","affiliation":"College of Computer and Information , Hohai University , Nanjing , China"},{"name":"Jun Zhou","slug":"jun-zhou","given":"Jun","family":"Zhou","affiliation":"School of Information and Communication Technology , Griffith University , Queensland , Australia"}],"abstract":"Transfer learning has been widely adopted for few-shot classification. Recent studies reveal that obtaining good generalization representation of images on novel classes is the key to improving the few-shot classification accuracy. To address this need, we prove theoretically that leveraging ensemble learning on the base classes can correspondingly reduce the true error in the novel classes. Following this principle, a novel method named Ensemble Learning with Multi-Order Statistics (ELMOS) is proposed in this paper. In this method, after the backbone network, we use multiple branches to create the individual learners in the ensemble learning, with the goal to reduce the storage cost. We then introduce different order statistics pooling in each branch to increase the diversity of the individual learners. The learners are optimized with supervised losses during the pre-training phase. After pre-training, features from different branches are concatenated for classifier evaluation. Extensive experiments demonstrate that each branch can complement the others and our method can produce a state-of-the-art performance on multiple few-shot classification benchmark datasets.","doi":"10.24963/ijcai.2023/181","url":"https://ijcai.org/proceedings/2023/181","pdf":"https://ijcai.org/proceedings/2023/0181.pdf","markdown":"https://ijcai.org/proceedings/2023/181.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/181","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":"Computer Vision","track":"Main Track","number":181,"pages":{"first":1631,"last":1639},"keywords":["Computer Vision: CV: Recognition (object detection, categorization)","Computer Vision: CV: Transfer, low-shot, semi- and un- supervised learning"],"videos":[],"references":[{"position":1,"raw":"[Afrasiyabi et al., 2020] Arman Afrasiyabi, Jean-Franc ¸ois Lalonde, and Christian Gagné. Associative alignment for few-shot image classification. In Proceedings of European Conference on Computer Vision, pages 18-35, Glasgow, UK, November 2020. Springer.","title":"Associative alignment for few-shot image classification","authors":"Arman Afrasiyabi, Jean-Franc ¸ois Lalonde, Christian Gagné","year":"2020","venue":"Proceedings of European Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Afrasiyabi et al., 2022] Arman Afrasiyabi, Hugo Larochelle, Jean-Franc ¸ois Lalonde, and Christian Gagné. Matching feature sets for few-shot image classification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9014-9024, New Orleans, USA, June 2022. IEEE.","title":"Matching feature sets for few-shot image classification","authors":"Arman Afrasiyabi, Hugo Larochelle, Jean-Franc ¸ois Lalonde, Christian Gagné","year":"2022","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Agarwal et al., 2021] Rishabh Agarwal, Levi Melnick, Nicholas Frosst, Xuezhou Zhang, , Rich Caruana, and Ge- offrey E Hinton. Neural additive models: Interpretable machine learning with neural nets. In Proceedings of 34th Annual Conference on Neural Information Process- ing Systems, pages 4078-4088, 4699-4711, December 2021. Neural Information Processing Systems Foundation.","title":"Neural additive models: Interpretable machine learning with neural nets","authors":"Rishabh Agarwal, Levi Melnick, Nicholas Frosst, Xuezhou Zhang, Rich Caruana, Geoffrey E Hinton","year":"2021","venue":"Proceedings of 34th Annual Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Baik et al., 2021] Sungyong Baik, Janghoon Choi, Heewon Kim, Dohee Cho, Jaesik Min, and Kyoung Mu Lee. Meta-learning with task-adaptive loss function for few- shot learning. In Proceedings of the IEEE/CVF Confer- ence on Computer Vision and Pattern Recognition, pages 9465-9474, Nashville, USA, June 2021. IEEE.","title":"Meta-learning with task-adaptive loss function for fewshot learning","authors":"Baik","year":"2021","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Bendou et al., 2022] Yassir Bendou, Yuqing Hu, Raphael Lafargue, Giulia Lioi, Stéphane Pateux, and Vincent Gripon. Easy-ensemble augmented-shot-y-shaped learn- ing: State-of-the-art few-shot classification with simple components. Journal of Imaging, 8(7):179, 2022.","title":"Easy-ensemble augmented-shot-y-shaped learning: State-of-the-art few-shot classification with simple components","authors":"Yassir Bendou, Yuqing Hu, Raphael Lafargue, Giulia Lioi, Stéphane Pateux, Vincent Gripon","year":"2022","venue":"Journal of Imaging","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Bertinetto et al., 2019] Luca Bertinetto, Joao F Henriques, Philip HS Torr, and Andrea Vedaldi. Meta-learning with differentiable closed-form solvers. In Proceedings of 7th International Conference on Learning Representations, New Orleans, USA, May 2019. International Conference on Learning Representations.","title":"Meta-learning with differentiable closed-form solvers","authors":"Luca Bertinetto, Joao F Henriques, Philip Hs Torr, Andrea Vedaldi","year":"2019","venue":"Proceedings of 7th International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Bouniot et al., 2022] Quentin Bouniot, Ievgen Redko, Ro- maric Audigier, Angélique Loesch, and Amaury Habrard. Improving few-shot learning through multi-task represen- tation learning theory. In Proceedings of European Confer- ence on Computer Vision, pages 435-452, Tel Aviv, Israel, October 2022. Springer.","title":"Improving few-shot learning through multi-task representation learning theory","authors":"Quentin Bouniot, Ievgen Redko, Romaric Audigier, Angélique Loesch, Amaury Habrard","year":"2022","venue":"Proceedings of European Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Chen et al., 2019] Wei-Yu Chen, Yen-Cheng Liu, Zsolt Kira, Yu-Chiang Frank Wang, and Jia-Bin Huang. A closer look at few-shot classification. In Proceedings of 7th In- ternational Conference on Learning Representations, New Orleans, USA, May 2019. International Conference on Learning Representations.","title":"A closer look at few-shot classification","authors":"Wei-Yu Chen, Yen-Cheng Liu, Zsolt Kira, Yu-Chiang Frank, Wang, Jia-Bin Huang","year":"2019","venue":"Proceedings of 7th International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Cui et al., 2017] Yin Cui, Feng Zhou, Jiang Wang, Xiao Liu, Yuanqing Lin, and Serge Belongie. Kernel pooling for convolutional neural networks. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 2921-2930, Venice, Italy, February 2017. IEEE. Dvornik et al., 2019]","title":"Kernel pooling for convolutional neural networks","authors":"Yin Cui, Feng Zhou, Jiang Wang, Xiao Liu, Yuanqing Lin, Serge Belongie","year":"2017","venue":"Proceedings of the IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"Nikita Dvornik, Cordelia Schmid, and Julien Mairal. Diversity with cooperation: Ensemble methods for few-shot classification. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 3723-3731, Seoul, Korea, February 2019. IEEE.","title":"Diversity with cooperation: Ensemble methods for few-shot classification","authors":"Nikita Dvornik, Cordelia Schmid, Julien Mairal","year":"2019","venue":"Proceedings of the IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Finn et al., 2017] Chelsea Finn, Pieter Abbeel, and Sergey Levine. Model-agnostic meta-learning for fast adapta- tion of deep networks. In Proceedings of International Conference on Machine Learning, pages 1126-1135, Syd- ney,Australia, July 2017.","title":"Model-agnostic meta-learning for fast adaptation of deep networks","authors":"Finn","year":"2017","venue":"Proceedings of International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Gidaris et al., 2019] Spyros Gidaris, Andrei Bursuc, Patrick Pérez, and Matthieu Cord. Boosting few-shot visual learning with self-supervision. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 8059-8068, Seoul, Korea, February 2019. IEEE. Horváth et al., 2021]","title":"Boosting few-shot visual learning with self-supervision","authors":"Spyros Gidaris, Andrei Bursuc, Patrick Pérez, Matthieu Cord","year":"2019","venue":"Proceedings of the IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"Miklós Z Horváth, Mark Niklas Müller, Marc Fischer, and Martin Vechev. Boosting randomized smoothing with variance reduced classifiers. arXiv preprint arXiv:2106.06946, 2021.","title":"Boosting randomized smoothing with variance reduced classifiers","authors":"Z Miklós, Mark Horváth, Marc Niklas Müller, Martin Fischer, Vechev","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Ionescu et al., 2015] Catalin Ionescu, Orestis Vantzos, and Cristian Sminchisescu. Matrix backpropagation for deep networks with structured layers. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 2965-2973, Santiago, Chile, February 2015. IEEE.","title":"Matrix backpropagation for deep networks with structured layers","authors":"Catalin Ionescu, Orestis Vantzos, Cristian Sminchisescu","year":"2015","venue":"Proceedings of the IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kang et al., 2021] Dahyun Kang, Heeseung Kwon, Juhong Min, and Minsu Cho. Relational embedding for few-shot classification. In Proceedings of the IEEE/CVF Confer- ence on Computer Vision and Pattern Recognition, pages 8822-8833, Nashville, USA, June 2021. IEEE.","title":"Relational embedding for few-shot classification","authors":"Kang","year":"2021","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Kifer et al., 2004] Daniel Kifer, Shai Ben-David, and Jo- hannes Gehrke. Detecting change in data streams. In Proceedings of the 31st International Conference on Very Large Databases, pages 180-191, Toronto, Canada;, September 2004.","title":"Detecting change in data streams","authors":"Daniel Kifer, Shai Ben-David, Johannes Gehrke","year":"2004","venue":"Proceedings of the 31st International Conference on Very Large Databases","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Morgan Kaufmann. Liu et al., 2020] Bin Liu, Yue Cao, Yutong Lin, , Ming- sheng Long, and Han Hu. Negative margin matters: Un- derstanding margin in few-shot classification. In Proceed- ings of European Conference on Computer Vision, pages 438-455, Glasgow, UK, November 2020. Springer.","title":"Negative margin matters: Understanding margin in few-shot classification","authors":"Bin Liu, Yue Cao, Yutong Lin, Mingsheng Long, Han Hu","year":"2020","venue":"Proceedings of European Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Ma et al., 2019] Jiawei Ma, Hanchen Xie, Guangxing Han, Shih-Fu Chang, Aram Galstyan, and Wael Abd-Almageed. Partner-assisted learning for few-shot image classification. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 10573-10582, Seoul, Korea, February 2019. IEEE.","title":"Partner-assisted learning for few-shot image classification","authors":"Jiawei Ma, Hanchen Xie, Guangxing Han, Shih-Fu Chang, Aram Galstyan, Wael Abd-Almageed","year":"2019","venue":"Proceedings of the IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Ma et al., 2022a] Rongkai Ma, Pengfei Fang, Gil Avraham, Yan Zuo, Tianyu Zhu, Tom Drummond, and Mehrtash Ha- randi. Learning instance and task-aware dynamic kernels for few-shot learning. In Proceedings of European Con- ference on Computer Vision\", pages 257-274. Springer, 2022.","title":"Learning instance and task-aware dynamic kernels for few-shot learning","authors":"Ma","year":"2022","venue":"Proceedings of European Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Ma et al., 2022b] Rongkai Ma, Pengfei Fang, Tom Drum- mond, and Mehrtash Harandi. Adaptive poincaré point to set distance for few-shot classification. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 1926-1934, Austin, Texas, August 2022. AAAI.","title":"Adaptive poincaré point to set distance for few-shot classification","authors":"Ma","year":"2022","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Mangla et al., 2020] Puneet Mangla, Nupur Kumari, Ab- hishek Sinha, Mayank Singh, , and Vineeth N Balasubra- manian. Charting the right manifold: Manifold mixup for few-shot learning. In Proceedings of IEEE Winter Confer- ence on Applications of Computer Vision (WACV), pages 2218-2227, Snowmass, USA, March 2020. IEEE.","title":"Charting the right manifold: Manifold mixup for few-shot learning","authors":"Puneet Mangla, Nupur Kumari, Abhishek Sinha, Mayank Singh, Vineeth N Balasubramanian","year":"2020","venue":"Proceedings of IEEE Winter Conference on Applications of Computer Vision (WACV)","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Rajasegaran et al., 2020] Jathushan Rajasegaran, Salman Khan, , Fahad Shahbaz Khan, and Mubarak Shah. Self- supervised knowledge distillation for few-shot learning. arXiv preprint arXiv:2006.09785, 2020.","title":"Selfsupervised knowledge distillation for few-shot learning","authors":"Rajasegaran","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Scott et al., 2021] Tyler R Scott, Andrew C Gallagher, and Michael C Mozer. von mises-fisher loss: An exploration of embedding geometries for supervised learning. In Pro- ceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10612-10622, Nashville, USA, June 2021. IEEE.","title":"von mises-fisher loss: An exploration of embedding geometries for supervised learning","authors":"Andrew C Tyler R Scott, Michael C Gallagher, Mozer","year":"2021","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Shiryaev, 2016] Albert N Shiryaev. Probability-1, vol- ume 95. Springer, 2016.","title":"Probability-1","authors":"N Albert, Shiryaev","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Snell et al., 2017] Jake Snell, Kevin Swersky, and Richard Zemel. Prototypical networks for few-shot learning. In Proceedings of 31st Annual Conference on Neural In- formation Processing Systems, pages 4078-4088, Long Beach, USA, December 2017. Neural Information Pro- cessing Systems Foundation.","title":"Prototypical networks for few-shot learning","authors":"Jake Snell, Kevin Swersky, Richard Zemel","year":"2017","venue":"Proceedings of 31st Annual Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Sung et al., 2021] Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang, Philip HS Torr, and Timothy M Hospedales. Exploring complementary strengths of invariant and equivariant representations for few-shot learning. In Pro- ceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10836-10846, Nashville, USA, June 2021. IEEE.","title":"Exploring complementary strengths of invariant and equivariant representations for few-shot learning","authors":"Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang, Timothy M Philip Hs Torr, Hospedales","year":"2021","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Tian et al., 2020] Yonglong Tian, Yue Wang, Dilip Krish- nan, Joshua B Tenenbaum, and Phillip Isola. Rethink- ing few-shot image classification: a good embedding is all you need? In Proceedings of European Conference on Computer Vision, pages 266-282, Glasgow, UK, Novem- ber 2020. Springer.","title":"Rethinking few-shot image classification: a good embedding is all you need?","authors":"Yonglong Tian, Yue Wang, Dilip Krishnan, Joshua B Tenenbaum, Phillip Isola","year":"2020","venue":"Proceedings of European Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Tseng et al., 2020] Hung-Yu Tseng, Hsin-Ying Lee, Jia- Bin Huang, and Ming-Hsuan Yang. Cross-domain few- shot classification via learned feature-wise transformation. arXiv preprint arXiv:2001.08735, 2020.","title":"Cross-domain fewshot classification via learned feature-wise transformation","authors":"Hung-Yu Tseng, Hsin-Ying Lee, Jia-Bin Huang, Ming-Hsuan Yang","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Wang et al., 2020] Zeyuan Wang, Yifan Zhao, Jia Li, and Yonghong Tian. Cooperative bi-path metric for few- shot learning. In Proceedings of the 29th ACM Interna- tional Conference on Multimedia, pages 1524-1532, Seat- tle, USA, October 2020. ACM.","title":"Cooperative bi-path metric for fewshot learning","authors":"Wang","year":"2020","venue":"Proceedings of the 29th ACM International Conference on Multimedia","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Wertheimer et al., 2021] Davis Wertheimer, Luming Tang, and Bharath Hariharan. Few-shot classification with fea- ture map reconstruction networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8012-8021, Nashville, USA, 2021.","title":"Few-shot classification with feature map reconstruction networks","authors":"Davis Wertheimer, Luming Tang, Bharath Hariharan","year":"2021","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Wu et al., 2021] Jiamin Wu, Tianzhu Zhang, Yongdong Zhang, and Feng Wu. Task-aware part mining network for few-shot learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8433-8442, Nashville, USA, June 2021. IEEE.","title":"Task-aware part mining network for few-shot learning","authors":"Jiamin Wu, Tianzhu Zhang, Yongdong Zhang, Feng Wu","year":"2021","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Xie et al., 2022] Jiangtao Xie, Fei Long, Jiaming Lv, Qi- long Wang, and Peihua Li. Joint distribution matters: deep brownian distance covariance for few-shot classification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7962-7971, New Orleans, USA, June 2022. IEEE.","title":"Joint distribution matters: deep brownian distance covariance for few-shot classification","authors":"Jiangtao Xie, Fei Long, Jiaming Lv, Qilong Wang, Peihua Li","year":"2022","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Xu et al., 2021a] Chengming Xu, Yanwei Fu, Chen Liu, Chengjie Wang, Jilin Li, Feiyue Huang, Li Zhang, and Xi- angyang Xue. Learning dynamic alignment via meta-filter for few-shot learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5182-5191, Nashville, USA, June 2021. IEEE.","title":"Learning dynamic alignment via meta-filter for few-shot learning","authors":"Xu","year":"2021","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Xu et al., 2021b] Jing Xu, Xinglin Pan, Xu Luo, Wenjie Pei, and Zenglin Xu. Exploring category-correlated fea- ture for few-shot image classification. arXiv preprint arXiv:2112.07224, 2021.","title":"Exploring category-correlated feature for few-shot image classification","authors":"Xu","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Yang et al., 2013] Jing Yang, Xiaoqin Zeng, Shuiming Zhong, and Shengli Wu. Effective neural network ensem- ble approach for improving generalization performance. IEEE transactions on neural networks and learning sys- tems, 24(6):878-887, 2013.","title":"Effective neural network ensemble approach for improving generalization performance","authors":"Jing Yang, Xiaoqin Zeng, Shuiming Zhong, Shengli Wu","year":"2013","venue":"IEEE transactions on neural networks and learning systems","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Yang et al., 2021] Shuo Yang, Lu Liu, and Min Xu. Free lunch for few-shot learning: distribution calibration. In Proceedings of 9th International Conference on Learning Representations, New Orleans, USA, May 2021. Interna- tional Conference on Learning Representations.","title":"Free lunch for few-shot learning: distribution calibration","authors":"Shuo Yang, Lu Liu, Min Xu","year":"2021","venue":"Proceedings of 9th International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Yu et al., 2022] Tianyuan Yu, Sen He, Yi-Zhe Song, and Tao Xiang. Hybrid graph neural networks for few-shot learning. In Proceedings of the AAAI Conference on Arti- ficial Intelligence, pages 3179-3187, Austin, Texas, 2022.","title":"Hybrid graph neural networks for few-shot learning","authors":"Tianyuan Yu, Sen He, Yi-Zhe Song, Tao Xiang","year":"2022","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Zhang et al., 2020a] Chi Zhang, Yujun Cai, Guosheng Lin, and Chunhua Shen. Deepemd: few-shot image classifica- tion with differentiable earth mover's distance and struc- tured classifiers. In Proceedings of the IEEE/CVF Confer- ence on Computer Vision and Pattern Recognition, pages 12203-12213, Seattle, USA, June 2020. IEEE.","title":"Deepemd: few-shot image classification with differentiable earth mover's distance and structured classifiers","authors":"Zhang","year":"2020","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Zhang et al., 2020b] Manli Zhang, Jianhong Zhang, , and Songfang Huang. Iept: Instance-level and episode-level pretext tasks for few-shot learning. In Proceedings of 7th International Conference on Learning Representations, Addis Ababa, Ethiopian Empire, May 2020. International Conference on Learning Representations.","title":"Iept: Instance-level and episode-level pretext tasks for few-shot learning","authors":"Zhang","year":"2020","venue":"Proceedings of 7th International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Zhou et al., 2021] Ziqi Zhou, Xi Qiu, Jiangtao Xie, Jianan Wu, and Chi Zhang. Binocular mutual learning for im- proving few-shot classification. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 8402-8411, Seoul, Korea, February 2021. IEEE.","title":"Binocular mutual learning for improving few-shot classification","authors":"Ziqi Zhou, Xi Qiu, Jiangtao Xie, Jianan Wu, Chi Zhang","year":"2021","venue":"Proceedings of the IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}