A Novel Doubly Reweighting Multisource Transfer Learning Framework

Ji, Dingcheng; Jiang, Yizhang; Qian, Pengjiang; Wang, Shitong

doi:10.1109/tetci.2018.2868326

Cited by 6 publications

(1 citation statement)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All the above studies do not effectively record evolutionary information, so they cannot guide the whole search process based on experience. In contrast, Bayesian optimization ( Frazier, 2018 ) assumes the search space as a Gaussian distribution, learns experience in search processes, and calculates better parameters iteratively ( Wistuba ; Gupta et al., 2017 ; Ji et al., 2019 ; Basha et al., 2021 ). However, these methods still cost enormous computing resources.…”

Section: Related Workmentioning

confidence: 99%

A novel heuristic target-dependent neural architecture search method with small samples

Rao

et al. 2022

Front. Plant Sci.

View full text Add to dashboard Cite

It is well known that crop classification is essential for genetic resources and phenotype development. Compared with traditional methods, convolutional neural networks can be utilized to identify features automatically. Nevertheless, crops and scenarios are quite complex, which makes it challenging to develop a universal classification method. Furthermore, manual design demands professional knowledge and is time-consuming and labor-intensive. In contrast, auto-search can create network architectures when faced with new species. Using rapeseed images for experiments, we collected eight types to build datasets (rapeseed dataset (RSDS)). In addition, we proposed a novel target-dependent search method based on VGGNet (target-dependent neural architecture search (TD-NAS)). The result shows that test accuracy does not differ significantly between small and large samples. Therefore, the influence of the dataset size on generalization is limited. Moreover, we used two additional open datasets (Pl@ntNet and ICL-Leaf) to test and prove the effectiveness of our method due to three notable features: (a) small sample sizes, (b) stable generalization, and (c) free of unpromising detections.

show abstract