Abstract
Fine-grained classification is a challenging problem with small inter-class variance and large intra-class variance. It becomes more difficult when only a few labeled training samples are available. Inspired by the procedure of human recognition that two similar objects are usually distinguished by comparing their key parts, we develop a novel few-shot fine-grained classification method, which learns to model the inter-class boundaries in human-like style, i.e., extracting key-part structure information of objects and performing part-by-part comparison. To this end, we first extract the key parts of objects by using the designed key-part detector, which are then encoded by our structure encoder for the final comparison. To tackle with the scarce labeled samples, we train the proposed network under the metric-based few-shot learning methodology. Experiments on benchmark datasets demonstrate the effectiveness of the proposed method compared with the state-of-the-art counterparts. Besides, extensive investigations are conducted to verify the contributions of the key components of our method.
Similar content being viewed by others
References
Alfassy A, Karlinsky L, Aides A, Shtok J, Harary S, Feris R, Giryes R, Bronstein A.M (2019) Laso: Label-set operations networks for multi-label few-shot learning. In: CVPR
Chen Y, Bai Y, Zhang W, Mei T (2019) Destruction and construction learning for fine-grained image recognition. In: CVPR. pp 5157–5166
Cui Y, Zhou F, Wang J, Liu X, Lin Y, Belongie S (2017) Kernel pooling for convolutional neural networks. In: CVPR
Fu J, Zheng H, Mei T. Look closer to see better: recurrent attention convolutional neural network for fine-grained image recognition. In: CVPR. pp 4476–4484
Fu J, Zheng H, Tao M (2017) Look closer to see better: recurrent attention convolutional neural network for fine-grained image recognition. In: CVPR
Goring C, Rodner E, Freytag A, Denzler J (2014) Nonparametric part transfer for fine-grained recognition. In: CVPR
He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: CVPR. pp 770–778
Horn GV, Branson S, Farrell R, Haber S, Belongie S (2015) Building a bird recognition app and large scale dataset with citizen scientists: the fine print in fine-grained dataset collection. In: CVPR
Horn G.V, Perona P (2017)The devil is in the tails: fine-grained classification in the wild. arXiv arXiv:1709.01450
Kim J, Kim T, Kim S, Yoo CD (2019) Edge-labeling graph neural network for few-shot learning. In: CVPR
Kong S, Fowlkes C (2017) Low-rank bilinear pooling for fine-grained classification. CVPR. pp 7025–7034
Kong S, Fowlkes C (2017) Low-rank bilinear pooling for fine-grained classification. In: CVPR
Li P, Xie J, Wang Q, Gao Z (2018) Towards faster training of global covariance pooling networks by iterative matrix square root normalization. In: CVPR
Li P, Xie J, Wang Q, Zuo W(2017) Is second-order information helpful for large-scale visual recognition? In: ICCV
Li W, Wang L, Xu J, Huo J, Gao Y, Luo J (2019)Revisiting local descriptor based image-to-class measure for few-shot learning. In: CVPR
Li W, Xu J, Huo J, Wang L, Luo J(2019) Distribution consistency based covariance metric networks for few-shot learning. In: AAAI
Lin TY, RoyChowdhury A, Maji S (2015) Bilinear CNN models for fine-grained visual recognition. In: ICCV
Liu J, Belhumeur PN (2013) Bird part localization using exemplar-based models with enforced pose and subcategory consistency. In: CVPR
Pfister T, Charles J, Zisserman A (2014) Domain-adaptive discriminative one-shot learning of gestures. In: ECCV
Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv arXiv:1804.02767
Snell J, Swersky K, Zemel RS (2017) Prototypical networks for few-shot learning. In: NeurIPS
Sung F, Yang Y, Zhang L, Xiang T, Torr PHS, Hospedales TM (2017) Learning to compare: Relation network for few-shot learning. In: CVPR
Vinyals O, Blundell C, Lillicrap T, Kavukcuoglu K, Wierstra D (2016) Matching networks for one shot learning. In: NeurIPS
Wah C, Branson S, Welinder P, Perona P, Belongie S (2011) The Caltech-UCSD birds 200-2011 dataset. California Institute of Technology
Wang K, Wang X, Zhang T, Cheng Y(2021) Few-shot learning with deep balanced network and acceleration strategy. Int J Mach Learn Cybern 1–12
Wang Y, Morariu VI, Davis LS. Learning a discriminative filter bank within a CNN for fine-grained recognition. In: CVPR. pp 4148–4157
Wang YX, Girshick R, Hebert M, Hariharan B (2018) Low-shot learning from imaginary data. In: CVPR
Wu Z, Li Y, Guo L, Jia K (2019) Parn: position-aware relation networks for few-shot learning. In: ICCV
Yuxiong W, Martial H (2016) Learning from small sample sets by combining unsupervised meta-training with CNNS. In: NeurIPS
Zhang L, Huang S, Liu W, Tao D (2019) Learning a mixture of granularity-specific experts for fine-grained categorization. In: CVPR
Zheng H, Fu J, Zha Z, Luo J. Looking for the devil in the details: learning trilinear attention sampling network for fine-grained image recognition. In: CVPR. 5012–5021
Zheng H, Fu J, Zha ZJ, Luo J (2019) Learning deep bilinear transformation for fine-grained image representation. In: NeurIPS
Zhong SH, Huang X, Xiao Z (2020) Fine-art painting classification via two-channel dual path networks. Int J Mach Learn Cybern 11(1):137–152
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Li, S., Feng, L., Xue, L. et al. Learning relations in human-like style for few-shot fine-grained image classification. Int. J. Mach. Learn. & Cyber. 14, 377–385 (2023). https://doi.org/10.1007/s13042-021-01473-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-021-01473-8