Few-shot Learning in Intelligent Agriculture: A Review of Methods and Applications

Yıl 2024, Cilt: 30 Sayı: 2, 216 - 228, 26.03.2024

Jing Nie Yichen Yuan Yang Li Huting Wang Jingbin Li Yi Wang Kangle Song Sezai Ercisli

https://doi.org/10.15832/ankutbd.1339516

Öz

Due to the high cost of data acquisition in many specific fields, such as intelligent agriculture, the available data is insufficient for the typical deep learning paradigm to show its superior performance. As an important complement to deep learning, few-shot learning focuses on pattern recognition tasks under the constraint of limited data, which can be used to solve practical problems in many application fields with data scarcity. This survey summarizes the research status, main models and representative achievements of few-shot learning from four aspects: model fine-tuning, meta-learning, metric learning and data enhancement, and especially introduces the few-shot learning-driven typical applications in intelligent agriculture. Finally, the current challenges of few-shot learning and its development trends in intelligent agriculture are prospected.

Anahtar Kelimeler

Few-shot learning, Intelligent agriculture, Meta-learning, Metric learning, Fine-tune, Data augmentation

Kaynakça

• Antoniou A, Edwards H & Storkey A (2018). How to train your MAML. arXiv preprint arXiv:1810.09502
• Antoniou A, Storkey A & Edwards H (2017). Data augmentation generative adversarial networks. arXiv preprint arXiv:1711.04340
• Argüeso D, Picon A, Irusta U, Medela A, San-Emeterio M G, Bereciartua A & Alvarez-Gila A (2020). Few-Shot Learning approach for plant disease classification using images taken in the field. Computers and Electronics in Agriculture 175: 105542
• Bargiel D (2017). A new method for crop classification combining time series of radar images and crop phenology information. Remote sensing of environment 198: 369-383
• Bartunov S & Vetrov D (2018). Few-shot generative modelling with generative matching networks. Paper presented at the International Conference on Artificial Intelligence and Statistics
• Boudiaf M, Kervadec H, Masud Z I, Piantanida P, Ben Ayed I & Dolz J (2021). Few-shot segmentation without meta-learning: A good transductive inference is all you need? Paper presented at the Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
• Chao X & Li Y (2022). Semisupervised Few-Shot Remote Sensing Image Classification Based on KNN Distance Entropy. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15: 8798-8805
• Chen L, Cui X & Li W (2021). Meta-learning for few-shot plant disease detection. Foods 10(10): 2441 Chen W Y, Liu Y C, Kira Z, Wang Y C F & Huang J B (2019). A closer look at few-shot classification. arXiv preprint arXiv:1904.04232
• Chen Z, Fu Y, Zhang Y, Jiang Y G, Xue X & Sigal L (2018). Semantic feature augmentation in few-shot learning. arXiv preprint arXiv:1804.05298, 86(89): 2
• Dhillon G S, Chaudhari P, Ravichandran A & Soatto S (2019). A baseline for few-shot image classification. arXiv preprint arXiv:1909.02729.
• Fan Z, Ma Y, Li Z & Sun J (2021). Generalized few-shot object detection without forgetting. Paper presented at the Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Finn C, Abbeel P & Levine S (2017). Model-agnostic meta-learning for fast adaptation of deep networks. Paper presented at the International conference on machine learning
• Fort S (2017). Gaussian prototypical networks for few-shot learning on omniglot. arXiv preprint arXiv:1708.02735
• Gao T, Fisch A & Chen D (2020). Making pre-trained language models better few-shot learners. arXiv preprint arXiv:2012.15723
• Gomes J C & Borges D L (2022). Insect pest image recognition: A few-shot machine learning approach including maturity stages classification. Agronomy, 12(8): 1733
• Gulcehre C, Chandar S & Bengio Y (2017). Memory augmented neural networks with wormhole connections. arXiv preprint arXiv:1701.08718
• Guo Y, Wang H, Clark R, Berretti S & Bennamoun M (2022). Deep learning for 3D vision. In (Vol. 16, pp. 567-569): Wiley Online Library
• Guo Y, Wang H, Hu Q, Liu H, Liu L & Bennamoun M (2020). Deep learning for 3d point clouds: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 43(12): 4338-4364
• Hamuda E, Mc Ginley B, Glavin M & Jones E (2017). Automatic crop detection under field conditions using the HSV colour space and morphological operations. Computers and Electronics in Agriculture 133: 97-107
• Hou R, Chang H, Ma B, Shan S & Chen X (2019). Cross attention network for few-shot classification. Advances in Neural Information Processing Systems 32 pp
• Howard J & Ruder (2018). Universal language model fine-tuning for text classification. arXiv preprint arXiv:1801.06146
• Hui B, Zhu P, Hu Q & Wang Q (2019). Self-attention relation network for few-shot learning. Paper presented at the 2019 IEEE international conference on Multimedia & Expo Workshops (ICMEW)
• Jang H, Kim J, Jo J E, Lee J & Kim J (2019). Mnnfast: A fast and scalable system architecture for memory-augmented neural networks. Paper presented at the Proceedings of the 46th International Symposium on Computer Architecture Ji Z, Chai X, Yu Y, Pang Y & Zhang Z (2020). Improved prototypical networks for few-shot learning. Pattern Recognition Letters 140: 81-87
• Ji Z, Zou X, Huang T & Wu S (2019). Unsupervised few-shot learning via self-supervised training. arXiv preprint arXiv:1912.12178
• Kaul P, Xie W & Zisserman A (2022). Label, verify, correct: A simple few shot object detection method. Paper presented at the Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
• Khodadadeh S, Boloni L & Shah M (2019). Unsupervised meta-learning for few-shot image classification. Advances in Neural Information Processing Systems 32 pp
• Koch G, Zemel R & Salakhutdinov R (2015). Siamese neural networks for one-shot image recognition. Paper presented at the ICML deep learning workshop
• Lee D H & Chung S Y (2021). Unsupervised embedding adaptation via early-stage feature reconstruction for few-shot classification. In International Conference on Machine Learning (pp. 6098-6108). PMLR
• Li Y & Chao X (2021a). Semi-supervised few-shot learning approach for plant diseases recognition. Plant Methods 17: 1-10
• Li Y & Chao X (2021b). Toward sustainability: trade-off between data quality and quantity in crop pest recognition. Frontiers in plant science 12: 2959
• Li Y & Ercisli S (2023). Data-efficient Crop Pest Recognition Based on KNN Distance Entropy. Sustainable Computing: Informatics and Systems, 100860 pp
• Li Y, Nie J & Chao X (2020). Do we really need deep CNN for plant diseases identification? Computers and Electronics in Agriculture 178: 105803
• Li Y & Yang J (2020). Few-shot cotton pest recognition and terminal realization. Computers and Electronics in Agriculture 169: 105240
• Li Y & Yang J (2021). Meta-learning baselines and database for few-shot classification in agriculture. Computers and Electronics in Agriculture 182: 106055
• Lin H, Tse R, Tang S K, Qiang Z P & Pau G (2022). The Positive Effect of Attention Module in Few-Shot Learning for Plant Disease Recognition. Paper presented at the 2022 5th International Conference on Pattern Recognition and Artificial Intelligence (PRAI)
• Liu B, Wang X, Dixit M, Kwitt R & Vasconcelos N (2018). Feature space transfer for data augmentation. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition
• Liu H, Qiu Q, Wu L, Li W, Wang B & Zhou Y (2022). Few-shot learning for name entity recognition in geological text based on GeoBERT. Earth Science Informatics 15(2): 979-991
• Liu Y, Lee J, Park M, Kim S, Yang E, Hwang S J & Yang Y (2018). Learning to propagate labels: Transductive propagation network for few-shot learning. arXiv preprint arXiv:1805.10002
• Ma Y, Bai S, An S, Liu W, Liu A, Zhen X & Liu X (2020). Transductive Relation-Propagation Network for Few-shot Learning. Paper presented at the IJCAI
• Mai S, Hu H & Xu J (2019). Attentive matching network for few-shot learning. Computer Vision and Image Understanding 187: 102781
• Mehrotra A & Dukkipati A (2017). Generative adversarial residual pairwise networks for one shot learning. arXiv preprint arXiv:1703.08033
• Nakamura A & Harada T (2019). Revisiting fine-tuning for few-shot learning. arXiv preprint arXiv:1910.00216 Nassar I, Herath S, Abbasnejad E, Buntine W & Haffari G (2021). All labels are not created equal: Enhancing semi-supervision via label grouping and co-training. Paper presented at the Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
• Nie J, Jiang J, Li Y, Wang H, Ercisli S & Lv L (2023). Data and domain knowledge dual‐driven artificial intelligence: Survey, applications, and challenges. Expert Systems, e13425
• Nie J, Wang N, Li J, Wang Y & Wang K (2022). Prediction of liquid magnetization series data in agriculture based on enhanced CGAN. Frontiers in plant science, 1883 pp
• Nie J, Wang Y, Li Y & Chao X (2022a). Artificial intelligence and digital twins in sustainable agriculture and forestry: a survey. Turkish Journal of Agriculture and Forestry 46(5): 642-661
• Nie J, Wang Y, Li Y & Chao X (2022b). Sustainable computing in smart agriculture: survey and challenges. Turkish Journal of Agriculture and Forestry 46(4): 550-566
• Nuthalapati S V & Tunga A (2021). Multi-domain few-shot learning and dataset for agricultural applications. Paper presented at the Proceedings of the IEEE/CVF International Conference on Computer Vision
• Pahde F, Puscas M, Klein T & Nabi M (2021). Multimodal prototypical networks for few-shot learning. Paper presented at the Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision Pandey S, Singh S & Tyagi V (2022). Meta-learning for Few-Shot Insect Pest Detection in Rice Crop. Paper presented at the International Conference on Advances in Computing and Data Sciences
• Parnami A & Lee M (2022). Learning from few examples: A summary of approaches to few-shot learning. arXiv preprint arXiv:2203.04291
• Rae J, Hunt J J, Danihelka I, Harley T, Senior A W, Wayne G, Lillicrap T (2016). Scaling memory-augmented neural networks with sparse reads and writes. Advances in Neural Information Processing Systems 29 pp
• Raghu A, Raghu M, Bengio S & Vinyals O (2019). Rapid learning or feature reuse? towards understanding the effectiveness of maml. arXiv preprint arXiv:1909.09157
• Rakelly K, Shelhamer E, Darrell T, Efros A & Levine S (2018). Conditional networks for few-shot semantic segmentation
• Santoro A, Bartunov S, Botvinick M, Wierstra D & Lillicrap T (2016). Meta-learning with memory-augmented neural networks. Paper presented at the International conference on machine learning
• Shen W, Shi Z & Sun J (2019). Learning from adversarial features for few-shot classification. arXiv preprint arXiv:1903.10225
• Snell J, Swersky K & Zemel R (2017). Prototypical networks for few-shot learning. Advances in Neural Information Processing Systems 30 pp
• Soh J W, Cho S & Cho N I (2020). Meta-transfer learning for zero-shot super-resolution. Paper presented at the Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
• Subbraj S D R, Rengarajan V V & Palaniswamy S (2023). Transfer Learning based Image Classification of Diseased Tomato Leaves with Optimal Fine-Tuning combined with Heat Map Visualization. Journal of Agricultural Sciences 29(4): 1003-1017
• Sun Q, Liu Y, Chen Z, Chua T S & Schiele B (2020). Meta-transfer learning through hard tasks. IEEE Transactions on Pattern Analysis and Machine Intelligence 44(3): 1443-1456. DOI: 10.1109/TPAMI.2020.3018506
• Sun Q, Liu Y, Chua T S & Schiele B (2019). Meta-transfer learning for few-shot learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 403-412)
• Sun X, Wang B, Wang Z, Li H, Li H & Fu K (2021). Research progress on few-shot learning for remote sensing image interpretation. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 14: 2387-2402. DOI: 10.1109/JSTARS.2021.3052869
• Sung F, Yang Y, Zhang L, Xiang T, Torr P H & Hospedales T M (2018). Learning to compare: Relation network for few-shot learning. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition
• Tian Y, Wang Y, Krishnan D, Tenenbaum J B & Isola P (2020). Rethinking few-shot image classification: a good embedding is all you need? Paper presented at the Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XIV 16
• Varol İ S, Çetin N & Kirnak H (2022). Evaluation of Image Processing Technique on Quality Properties of Chickpea Seeds (Cicer arietinum L.) Using Machine Learning Algorithms. Journal of Agricultural Sciences 29(2): 427-442
• Vinyals O, Blundell C, Lillicrap T & Wierstra D (2016). Matching networks for one shot learning. Advances in Neural Information Processing Systems 29 pp
• Volkan K, Akgül İ & Tanır Ö Z (2023). IsVoNet8: A Proposed Deep Learning Model for Classification of Some Fish Species. Journal of Agricultural Sciences 29(1): 298-307.
• Wang N, Nie J, Li J, Wang K & Ling S (2022). A compression strategy to accelerate LSTM meta-learning on FPGA. ICT Express 8(3): 322-327
• Wang Y & Wang S (2021). Imal: An improved meta-learning approach for few-shot classification of plant diseases. Paper presented at the 2021 IEEE 21st International Conference on Bioinformatics and Bioengineering (BIBE).
• Wang Y, Yao Q, Kwok J T & Ni L M (2020). Generalizing from a few examples: A survey on few-shot learning. ACM computing surveys (csur), 53(3): 1-34
• Wu Z, Li Y, Guo L & Jia K (2019). Parn: Position-aware relation networks for few-shot learning. Paper presented at the Proceedings of the IEEE/CVF international conference on computer vision Xian Y, Sharma S, Schiele B & Akata Z (2019). f-vaegan-d2: A feature generating framework for any-shot learning. Paper presented at the Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
• Yang J, Guo X, Li Y, Marinello F, Ercisli S & Zhang Z (2022). A survey of few-shot learning in smart agriculture: developments, applications, and challenges. Plant Methods 18(1): 1-12
• Yang J, Lan G, Li Y, Gong Y, Zhang Z & Ercisli S (2022). Data quality assessment and analysis for pest identification in smart agriculture. Computers and Electrical Engineering 103: 108322
• Yang J, Ma S, Li Y & Zhang Z (2022). Efficient data-driven crop pest identification based on edge distance-entropy for sustainable agriculture. Sustainability 14(13): 7825
• Yang L, Li Y, Wang J & Xiong N N (2020). FSLM: An intelligent few-shot learning model based on Siamese networks for IoT technology. IEEE Internet of Things Journal 8(12): 9717-9729
• Yang Y, Li Y, Yang J & Wen J (2022). Dissimilarity-based active learning for embedded weed identification. Turkish Journal of Agriculture and Forestry 46(3): 390-401
• Yang Y, Zhang Z, Mao W, Li Y & Lv C (2021). Radar target recognition based on few-shot learning. Multimedia Systems pp. 1-11
• Yin S, Zhao W, Jiang X & He T (2020). Knowledge-aware few-shot learning framework for biomedical event trigger identification. Paper presented at the 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).
• Zhao W, Yamada W, Li T, Digman M & Runge T (2020). Augmenting crop detection for precision agriculture with deep visual transfer learning—a case study of bale detection. Remote Sensing 13(1): 23
• Zheng Y Y, Kong J L, Jin X B, Wang X Y, Su T L & Zuo M (2019). CropDeep: The crop vision dataset for deep-learning-based classification and detection in precision agriculture. Sensors 19(5): 1058
• Zhong L, Hu L & Zhou H (2019). Deep learning based multi-temporal crop classification. Remote sensing of environment 221: 430-443
• Zhou J, Zheng Y, Tang J, Li J & Yang Z (2021). Flipda: Effective and robust data augmentation for few-shot learning. arXiv preprint arXiv:2108.06332.
• Zhou X, Liang W, Shimizu S, Ma J & Jin Q (2020). Siamese neural network based few-shot learning for anomaly detection in industrial cyber-physical systems. IEEE Transactions on Industrial Informatics, 17(8): 5790-5798