Abstract
Plant diseases serve as one of main threats to food security and crop production. It is thus valuable to exploit recent advances of artificial intelligence to assist plant disease diagnosis. One popular approach is to transform this problem as a leaf image classification task, which can be then addressed by the powerful convolutional neural networks (CNNs). However, the performance of CNN-based classification approach depends on a large amount of high-quality manually labeled training data, which inevitably introduce noise on labels in practice, leading to model overfitting and performance degradation. To overcome this problem, we propose a novel framework that incorporates rectified meta-learning module into common CNN paradigm to train a noise-robust deep network without using extra supervision information. The proposed method enjoys the following merits: (i) A rectified meta-learning is designed to pay more attention to unbiased samples, leading to accelerated convergence and improved classification accuracy. (ii) Our method is free on assumption of label noise distribution, which works well on various kinds of noise. (iii) Our method serves as a plug-and-play module, which can be embedded into any deep models optimized by gradient descent-based method. Extensive experiments are conducted to demonstrate the superior performance of our algorithm over the state-of-the-arts.
- [1] . 2016. Metalearning with memory-augmented neural networks. In IEEE International Conference on Machine Learning. Google Scholar
Digital Library
- [2] . 2016. Learning to learn by gradient descent by gradient descent. In Conference on Advances in Neural Information Processing Systems. Google Scholar
Digital Library
- [3] . 2018. Factors influencing the use of deep learning for plant disease recognition. Biosyst. Eng. 172 (2018), 84–91.Google Scholar
Cross Ref
- [4] . 2005. Plant disease: A threat to global food security. Ann. Rev. Phytopathol. 43, 1 (2005), 83–116.Google Scholar
Cross Ref
- [5] . 2017. Learning to learn without gradient descent by gradient descent. Proc. Mach. Learn. Res. 70 (2017), 748–756. Google Scholar
Digital Library
- [6] . 2015. Metalearning: A survey of trends and technologies. Artif. Intell. Rev. 44, 1 (2015), 117–130. Google Scholar
Digital Library
- [7] . 2018. Using trusted data to train deep networks on labels corrupted by severe noise. In Conference and Workshop on Neural Information Processing Systems (NeurIPS). Google Scholar
Digital Library
- [8] . 2015. Gradient-based hyperparameter optimization through reversible learning. In 32nd International Conference on Machine Learning. Google Scholar
Digital Library
- [9] 2018. Deep learning models for plant disease detection and diagnosis. Comput. Electron. Agricult. 145 (2018), 311–318.Google Scholar
Cross Ref
- [10] . 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In IEEE International Conference on Machine Learning (ICML). Google Scholar
Digital Library
- [11] . 2017. Automatic image-based plant disease severity estimation using deep learning. Comput. Intell. Neurosci. 2017 (2017), 1–8.Google Scholar
- [12] . 2019. Deep self-learning from noisy labels. In IEEE International Conference on Computer Vision (ICCV) (2019).Google Scholar
- [13] . 2014. Extreme vulnerability of smallholder farmers to agricultural risks and climate change in madagascar. Philos. Trans. Roy. Societ. Lond. 369, 1639 (2014), 20130089.Google Scholar
Cross Ref
- [14] . 2001. Learning to learn using gradient descent. In International Conference on Artificial Neural Networks. Google Scholar
Digital Library
- [15] . 2015. An open access repository of images on plant health to enable the development of mobile disease diagnostics through machine learning and crowdsourcing. Comput. Sci. (2015).Google Scholar
- [16] . 2016. Training deep neural-networks using a noise adaptation layer. In IEEE International Conference on Learning Representations (ICLR).Google Scholar
- [17] . 2017. Prototypical networks for few-shot learning. In Conference and Workshop on Neural Information Processing Systems (NeurIPS). Google Scholar
Digital Library
- [18] . 2016. An enhancement in classifier support vector machine to improve plant disease detection. In IEEE International Conference on MOOCs, Innovation and Technology in Education. 135–140.Google Scholar
- [19] . 2015. Plant disease detection using image processing. In International Conference on Computing Communication Control and Automation. IEEE Computer Society. Google Scholar
Digital Library
- [20] . 2019. NLNL: Negative learning for noisy labels. In IEEE/CVF International Conference on Computer Vision (ICCV). 101–110.Google Scholar
Cross Ref
- [21] . 2009. Learning Multiple Layers of Features from Tiny Images. Master’s Thesis. University of Toronto.Google Scholar
- [22] . 2010. Self-paced learning for latent variable models. In Conference and Workshop on Neural Information Processing Systems (NeurIPS). Google Scholar
Digital Library
- [23] . 2018. CleanNet: Transfer learning for scalable image classifier training with label noise. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Google Scholar
Cross Ref
- [24] . 2019. Learning to learn from noisy labeled data. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5051–5059.Google Scholar
- [25] . 2018. Learning from noisy web data with category level supervision. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Google Scholar
- [26] . 2017. Learning from noisy labels with distillation. In IEEE International Conference on Computer Vision (ICCV). 1928–1936.Google Scholar
Cross Ref
- [27] . 2017. Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. PP, 99 (2017), 2999–3007.Google Scholar
- [28] . 2017. Self-error-correcting convolutional neural network for learning with noisy labels. In 12th IEEE International Conference on Automatic Face Gesture Recognition (FG’17). 111–117.Google Scholar
Cross Ref
- [29] . 2011. Ensemble of exemplar-SVMs for object detection and beyond. In IEEE International Conference on Computer Vision (ICCV). Google Scholar
Digital Library
- [30] . 2016. Using deep learning for image-based plant disease detection. Front. Plant Sci. 7 (2016), 1419.Google Scholar
Cross Ref
- [31] . 2016. Matching networks for one shot learning. In Conference and Workshop on Neural Information Processing Systems (NeurIPS). Google Scholar
Digital Library
- [32] . 2017. Making deep neural networks robust to label noise: A loss correction approach. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1944–1952.Google Scholar
- [33] . 2015. Training deep convolutional networks on noisy labels with bootstrapping. In IEEE International Conference on Learning Representations (ICLR).Google Scholar
- [34] . 2018. CurriculumNet: Weakly supervised learning from large-scale web images. In European Conference on Computer Vision.Google Scholar
- [35] . 2014. Training convolutional networks with noisy labels. In IEEE International Conference on Learning Representations (ICLR).Google Scholar
- [36] . 2018. Joint optimization framework for learning with noisy labels. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 5552–5560.Google Scholar
- [37] . 2017. Learning from noisy large-scale datasets with minimal supervision. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Google Scholar
- [38] . 2001. A perspective view and survey of meta-learning. Artif. Intell. Rev. 18, 2 (2001). Google Scholar
Digital Library
- [39] . 2016. Detection and classification of diseases of grape plant using opposite colour local binary pattern feature and machine learning for automated decision support system. In International Conference on Signal Processing and Integrated Networks. IEEE.Google Scholar
- [40] . 2016. Learning to reinforcement learn. In Annual Meeting of the Cognitive Science Society.Google Scholar
- [41] . 2018. Iterative learning with open-set noisy labels. In IEEE/CVF Conference on Computer Vision and Pattern Recognition. 8688–8696.Google Scholar
Cross Ref
- [42] . 2019. Symmetric cross entropy for robust learning with noisy labels. In IEEE International Conference on Computer Vision.Google Scholar
Cross Ref
- [43] . 2019. Co-mining: Deep face recognition with noisy labels. In IEEE International Conference on Computer Vision (ICCV).Google Scholar
- [44] . 2019. Probabilistic end-to-end noise correction for learning with noisy labels. CoRR (2019).
arxiv:1903.07788 .Google Scholar - [45] . 2018. Generalized cross entropy loss for training deep neural networks with noisy labels. In Conference and Workshop on Neural Information Processing Systems (NeurIPS).Google Scholar
- [46] . 2017. Meta-SGD: Learning to learn quickly for few shot learning. arXiv:1707.09835 (2017).Google Scholar
Index Terms
Rectified Meta-learning from Noisy Labels for Robust Image-based Plant Disease Classification
Recommendations
Collaborative Learning with Pseudo Labels for Robust Classification in the Presence of Noisy Labels
Computer Vision – ECCV 2020 WorkshopsAbstractSupervised learning depends on labels of dataset to train models with desired properties. Therefore, data containing mislabeled samples (a.k.a. noisy labels) can deteriorate supervised learning performance significantly as it makes models to be ...
How to handle noisy labels for robust learning from uncertainty
AbstractMost deep neural networks (DNNs) are trained with large amounts of noisy labels when they are applied. As DNNs have the high capacity to fit any noisy labels, it is known to be difficult to train DNNs robustly with noisy labels. These ...
Meta joint optimization: a holistic framework for noisy-labeled visual recognition
AbstractCollecting large-scale data with clean labels for supervised training is practically challenging. It is easier to collect a dataset with noisy labels, but such noise may degrade the performance of deep neural networks (DNNs). This paper targets at ...






Comments