[1]ZHOU Kairui,LIU Xin,JING Liping,et al.Concept-driven discriminative feature learning for few-shot learning[J].CAAI Transactions on Intelligent Systems,2023,18(1):162-172.[doi:10.11992/tis.202203061]
Copy

Concept-driven discriminative feature learning for few-shot learning

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 18 Number of periods: 2023 1 Page number: 162-172 Column: 人工智能院长论坛 Public date: 2023-01-05
Title:
Concept-driven discriminative feature learning for few-shot learning
Author(s):
ZHOU Kairui1; 2;  LIU Xin1; 2;  JING Liping1; 2;  YU Jian1; 2
1. Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing 100044, China;
2. School of Computer Science and Technology, Beijing Jiaotong University, Beijing 100044, China
Keywords:
few-shot learning; metric learning; class representation; discriminative feature learning; data augmentation; image classification; neural network; deep learning
CLC:
TP18
DOI:
10.11992/tis.202203061
Abstract:
Few-shot learning (FSL) aims to recognize unlabeled samples from novel classes with few labeled samples. Metric-based methods, which obtain favorable results in FSL, construct class representations with labeled samples and classify the query samples based on the similarity between class representations and query samples. Therefore, constructing discriminative class representations is the key to these approaches. Most of the existing work ignores the mining of concept-relevant discriminative sample information when constructing class representations, which may bring noise information in samples to the class representations. To alleviate these problems, a concept-driven discriminative feature learning method tailored for FSL is proposed in this work. First, this method incorporates semantic category information to guide the mining of the class-sensitive information of labeled samples and thereby establishes a more discriminative class representation. Then, a random mask mixing mechanism is designed to increase data diversity and the identification difficulty of query samples to further improve class representation quality. Finally, it assigns higher weights to the samples near the decision boundary to guide the model to focus on difficult samples, which helps to learn better class representations. Extensive experiments show that the framework proposed in this work can effectively improve recognition accuracy, and it outperforms state-of-the-art methods on many benchmarks.
References:
[1] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770?778.
[2] SNELL J, SWERSKY K, ZEMEL R S. Prototypical networks for few-shot learning[C]//Advances in Neural Information Processing Systems. Cambridge: MIT Press, 2017: 4077? 4087.
[3] SUNG F, YANG Yongxin, ZHANG Li, et al. Learning to compare: relation network for few-shot learning[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 1199?1208.
[4] CHEN Weiyu, LIU Yencheng, KIRA Z, et al. A closer look at few-shot classification[C]//Proceedings of the International Conference on Learning Representations. LaJolla, CA: ICLR, 2018.
[5] ZHANG Chi, CAI Yujun, LIN Guosheng, et al. DeepEMD: few-shot image classification with differentiable earth mover’s distance and structured classifiers[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 12200?12210.
[6] YE Hanjia, HU Hexiang, ZHAN Dechuan, et al. Few-shot learning via embedding adaptation with set-to-set functions[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 8805-8814.
[7] LI Wenbin, WANG Lei, XU Jinglin, et al. Revisiting local descriptor based image-to-class measure for few-shot learning[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 7253?7260.
[8] ORESHKIN B N, RODRIGUEZ P, LACOSTE A. TADAM: Task dependent adaptive metric for improved few-shot learning[C]//Proceedings of the 32nd International Conference on Neural Information Processing Systems. Cambridge: MIT Press, 2018: 719?729
[9] SACHIN Ravi, HUGO Larochelle. Optimization as a model for few-shot learning [C]//Proceedings of the International Conference on Learning Representations. LaJolla: ICLR, 2017.
[10] FINN C, ABBEEL P, LEVINE S. Model-agnostic meta-learning for fast adaptation of deep networks[C]//International Conference on Machine Learning. New York: ACM, 2017: 1126?1135.
[11] VINYALS O, BLUNDELL C, LILLICRAP T, et al. Matching networks for one shot learning[C]//Proceedings of the 30th International Conference on Neural Information Processing Systems. Cambridge: MIT Press, 2016: 3637?3645.
[12] HOU R, CHANG H, MA B, et al. Cross attention network for few-shot classification[C]//Advances in Neural Informa-tion Processing Systems. Cambridge: MIT Press, 2019: 4003?4014.
[13] XING C, ROSTAMZADEH N, ORESHKIN B N, et al. Adaptive cross-modal few-shot learning[C]//Advances in Neural Information Processing Systems. Cambridge: MIT Press, 2019: 4847?4857.
[14] LIFCHITZ Y, AVRITHIS Y, PICARD S, et al. Dense classification and implanting for few-shot learning[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 9250?9259.
[15] 王德文, 魏波涛. 基于孪生变分自编码器的小样本图像分类方法[J]. 智能系统学报, 2021, 16(2): 254–262
WANG Dewen, WEI Botao. A small-sample image classification method based on a Siamese variational auto-encoder[J]. CAAI Transactions on Intelligent Systems, 2021, 16(2): 254–262
[16] 张玲玲, 陈一苇, 吴文俊, 等. 基于对比约束的可解释小样本学习[J]. 计算机研究与展, 2021, 58(12): 2573–2584
ZHANG Lingling, CHEN Yiwei, WU Wenjun, et al. Interpretable few-shot learning with contrastive constraint[J]. Journal of computer research and development, 2021, 58(12): 2573–2584
[17] 韦世红, 刘红梅, 唐宏, 等. 多级度量网络的小样本学习[J/OL]. 计算机工程与应用, 2021: 1?10. (2021?10?12) [2023?01?05]. https://kns.cnki.net/kcms/detail/11.2127.TP.20211012.1508.008.html.
WEI Shihong, LIU Hongmei, TANG Hong, et al. Multilevel metric networks for few-ShotLearning[J/OL]. Computer engineering and applications, 2021: 1?10. (2021?10?12) [2023?01?05]. https://kns.cnki.net/kcms/detail/11.2127.TP.20211012.1508.008.html.
[18] ZHENG Yan, WANG Ronggui, YANG Juan, et al. Principal characteristic networks for few-shot learning[J]. Journal of visual communication and image representation, 2019, 59: 563–573.
[19] XU Chengming, FU Yanwei, LIU Chen, et al. Learning dynamic alignment via meta-filter for few-shot learning[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Nashville. IEEE, 2021: 5178-5187.
[20] GARCIA V, BRUNA J. Few-shot learning with graph neural networks[C]//Proceedings of the International Conference on Learning Representations. LaJolla: ICLR, 2018.
[21] ZHANG H, CISSE M, DAUPHIN Y N, et al. Mixup: Beyond empirical risk minimization[C]//Proceedings of the Interna-tional Conference on Learning Representations. LaJolla: ICLR, 2018.
[22] YUN S, HAN D, CHUN S, et al. CutMix: regularization strategy to train strong classifiers with localizable features[C]//2019 IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2019: 6022?6031.
[23] VERMA V, LAMB A, BECKHAM C, et al. Manifold mixup: Better representations by interpolating hidden states[C]// International Conference on Machine Learning. New York: ACM, 2019: 6438?6447.
[24] WANG Yuxiong, GIRSHICK R, HEBERT M, et al. Low-shot learning from imaginary data[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 7278?7286.
[25] NI R, GOLDBLUM M, SHARAF A, et al. Data augmentation for meta-learning[C]//International Conference on Machine Learning. New York: ACM, 2021: 8152?8161.
[26] SEO J W, JUNG H G, LEE S W. Self-augmentation: Generalizing deep networks to unseen classes for few-shot learning[J]. Neural networks, 2021, 138: 140–149.
[27] MANGLA P, SINGH M, SINHA A, et al. Charting the right manifold: manifold mixup for few-shot learning[C]//2020 IEEE Winter Conference on Applications of Computer Vision. Snowmass: IEEE, 2020: 2207?2216.
[28] LIU Jialin, CHAO Fei, LIN C M. Task augmentation by rotating for meta-learning[EB/OL]. (2020?02?08)[2022?03?01].https://arxiv.org/abs/2003.00804.
[29] KIM J H, ON K W, LIM W, et al. Hadamard product for low-rank bilinear pooling[C] //Proceedings of the International Conference on Learning Representations. LaJolla: ICLR, 2017 : 04325.
[30] PENNINGTON J, SOCHER R, MANNING C. Glove: global vectors for word representation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Doha: Association for Computational Linguistics, 2014: 1532?1543.
[31] LIU Chen, FU Yanwei, XU Chengming, et al. Learning a few-shot embedding model with contrastive learning[J]. Proceedings of the AAAI conference on artificial intelligence, 2021, 35(10): 8635–8643.
[32] REN Mengye, TRIANTAFILLOU E, RAVI S, et al. Meta-learning for semi-supervised few-shot classification[EB/OL]. (2018?03?02)[2022?03?01].https://arxiv.org/abs/1803.00676.
[33] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C]//NIPS’12: Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 1. New York: ACM, 2012: 1097-1105.
[34] KRIZHEVSKY A. Learning multiple layers of features from tiny images[M]. Cambridge: MIT Press, 2009.
[35] LEE K, MAJI S, RAVICHANDRAN A, et al. Meta-learning with differentiable convex optimization[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 10649?10657.
[36] RUSU A A, RAO D, SYGNOWSKI J, et al. Meta-Learning with Latent Embedding Optimization[C]//International Conference on Learning Representations. LaJolla: ICLR, 2018.
[37] WANG Yikai, XU Chengming, LIU Chen, et al. Instance credibility inference for few-shot learning[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 12833?12842.
[38] TIAN Yonglong, WANG Yue, KRISHNAN D, et al. Rethinking few-shot image classification: a good embedding is all you need? [M]//Computer Vision ECCV 2020. Cham: Springer International Publishing, 2020: 266?282.
[39] ZHOU Ziqi, QIU Xi, XIE Jiangtao, et al. Binocular mutual learning for improving few-shot classification[C]//2021 IEEE/CVF International Conference on Computer Vision. Montreal: IEEE, 2021: 8382-8391.
[40] WAH C, BRANSON S, WELINDER P, et al. The caltech-ucsd birds-200-2011 dataset[EB/OL]. (2011?10?26)[2022?03?01]. https://authors.library.caltech.edu/27452.
[41] LIU Bin, CAO Yue, LIN Yutong, et al. Negative margin matters: understanding margin in few-shot classification[M]//Computer Vision – ECCV 2020. Cham: Springer International Publishing, 2020: 438?455.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems