DAMSL: Domain Agnostic Meta Score-based Learning

Cai, John; Cai, Bill; Mei, Shen

doi:10.1109/cvprw53098.2021.00292

Cited by 4 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cai et al. (2021) propose a powerful few‐shot cross‐domain method using the Graph Neural Network as a key metric that can work in several specialized fields such as plant disease identification. In short, this type of meta‐learning method is more suitable for few‐shot tasks and can effectively solve the limitation of datasets in plant disease recognition.…”

Section: Methods Of Meta‐learning In Plant Disease Recognitionmentioning

confidence: 99%

“…Similarly, Cai et al. (2021) exploit Graph Neural Networks (Garcia & Bruna, 2017) to mine graph knowledge relationships for graphical features of agricultural diseases, achieving favorable migration capability of the model when the study domain changes for few‐shot learning. It is worth noting that, because the PlantVillage dataset also contains disease images of several fruits, the above method also has some ability to identify fruit diseases.…”

Section: Applications Of Meta‐learning In Plant Disease Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

Meta‐learning shows great potential in plant disease recognition under few available samples

Deng

Wang

et al. 2023

The Plant Journal

View full text Add to dashboard Cite

Plant diseases worsen the threat of food shortage with the growing global population, and disease recognition is the basis for the effective prevention and control of plant diseases. Deep learning has made significant breakthroughs in the field of plant disease recognition. Compared with traditional deep learning, metalearning can still maintain more than 90% accuracy in disease recognition with small samples. However, there is no comprehensive review on the application of meta-learning in plant disease recognition. Here, we mainly summarize the functions, advantages, and limitations of meta-learning research methods and their applications for plant disease recognition with a few data scenarios. Finally, we outline several research avenues for utilizing current and future meta-learning in plant science. This review may help plant science researchers obtain faster, more accurate, and more credible solutions through deep learning with fewer labeled samples.

show abstract

Section: Methods Of Meta‐learning In Plant Disease Recognitionmentioning

confidence: 99%

Section: Applications Of Meta‐learning In Plant Disease Recognitionmentioning

confidence: 99%

Meta‐learning shows great potential in plant disease recognition under few available samples

Deng

Wang

et al. 2023

The Plant Journal

View full text Add to dashboard Cite

show abstract

“…Particularly, PMF contributes a simple pipeline and builds a SOTA for FSL. As an extended task from FSL, CD-FSL [1,6,10,11,17,18,25,32,35,42,49,53,57] mainly solves the FSL across different domains. Typical meta-learning based CD-FSL methods include FWT [53], LRP [49], ATA [57], AFA [22], and wave-SAN [11].…”

Section: Related Workmentioning

confidence: 99%

Meta Style Adversarial Training for Cross-Domain Few-Shot Learning

Fu¹,

Xie²,

Fu³

et al. 2023

Preprint

View full text Add to dashboard Cite

Cross-Domain Few-Shot Learning (CD-FSL) is a recently emerging task that tackles few-shot learning across different domains. It aims at transferring prior knowledge learned on the source dataset to novel target datasets. The CD-FSL task is especially challenged by the huge domain gap between different datasets. Critically, such a domain gap actually comes from the changes of visual styles, and wave-SAN [11] empirically shows that spanning the style distribution of the source data helps alleviate this issue. However, wave-SAN simply swaps styles of two images. Such a vanilla operation makes the generated styles "real" and "easy", which still fall into the original set of the source styles. Thus, inspired by vanilla adversarial learning, a novel model-agnostic meta Style Adversarial training (StyleAdv) method together with a novel style adversarial attack method is proposed for CD-FSL. Particularly, our style attack method synthesizes both "virtual" and "hard" adversarial styles for model training. This is achieved by perturbing the original style with the signed style gradients. By continually attacking styles and forcing the model to recognize these challenging adversarial styles, our model is gradually robust to the visual styles, thus boosting the generalization ability for novel target datasets. Besides the typical CNN-based backbone, we also employ our StyleAdv method on large-scale pretrained vision transformer. Extensive experiments conducted on eight various target datasets show the effectiveness of our method. Whether built upon ResNet or ViT, we achieve the new state of the art for CD-FSL. Codes and models will be released.

show abstract

“…Recent study [9] finds that most of the existing FSL methods [12, 15, 17, 28, 37, 37, 39, 41-43, 46, 52-54] that assume the source and target datasets belong to the same distribution fail to generalize to novel datasets with a domain gap. Thus, CD-FSL which aims at addressing FSL across different domains has risen increasing attentions [4,13,14,18,24,33,40,44,48]. In this paper, these CD-FSL methods are categorized according to which kind of data are being used for training: 1) CD-FSL with only source data [14,40,44,48]; 2) CD-FSL with unlabeled target data [24,33]; 3) CD-FSL with labeled target data [13].…”

Section: Related Workmentioning

confidence: 99%

ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learning

Xie

et al. 2022

Proceedings of the 30th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Recently, Cross-Domain Few-Shot Learning (CD-FSL) which aims at addressing the Few-Shot Learning (FSL) problem across different domains has attracted rising attention. The core challenge of CD-FSL lies in the domain gap between the source and novel target datasets. Though many attempts have been made for CD-FSL without any target data during model training, the huge domain gap makes it still hard for existing CD-FSL methods to achieve very satisfactory results. Alternatively, learning CD-FSL models with few labeled target domain data which is more realistic and promising is advocated in previous work [13]. Thus, in this paper, we stick to this setting and technically contribute a novel Multi-Expert Domain Decompositional Network (ME-D2N). Concretely, to solve the data imbalance problem between the source data with sufficient examples and the auxiliary target data with limited examples, we build our model under the umbrella of multi-expert * indicates equal contributions, # indicates corresponding author.

show abstract

DAMSL: Domain Agnostic Meta Score-based Learning

Cited by 4 publications

References 10 publications

Meta‐learning shows great potential in plant disease recognition under few available samples

Meta‐learning shows great potential in plant disease recognition under few available samples

Meta Style Adversarial Training for Cross-Domain Few-Shot Learning

ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learning

Contact Info

Product

Resources

About