Meta-learning approaches for few-shot learning: A survey of recent advances

H Gharoun, F Momenifar, F Chen… - ACM Computing …, 2024 - dl.acm.org
Despite its astounding success in learning deeper multi-dimensional data, the performance
of deep learning declines on new unseen tasks mainly due to its focus on same-distribution …

Learning attention-guided pyramidal features for few-shot fine-grained recognition

H Tang, C Yuan, Z Li, J Tang - Pattern Recognition, 2022 - Elsevier
Few-shot fine-grained recognition (FS-FGR) aims to distinguish several highly similar
objects from different sub-categories with limited supervision. However, traditional few-shot …

Hierarchical graph neural networks for few-shot learning

C Chen, K Li, W Wei, JT Zhou… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Recent graph neural network (GNN) based methods for few-shot learning (FSL) represent
the samples of interest as a fully-connected graph and conduct reasoning on the nodes …

Boosting few-shot fine-grained recognition with background suppression and foreground alignment

Z Zha, H Tang, Y Sun, J Tang - IEEE Transactions on Circuits …, 2023 - ieeexplore.ieee.org
Few-shot fine-grained recognition (FS-FGR) aims to recognize novel fine-grained categories
with the help of limited available samples. Undoubtedly, this task inherits the main …

Few-shot named entity recognition: Definition, taxonomy and research directions

V Moscato, M Postiglione, G Sperlí - ACM Transactions on Intelligent …, 2023 - dl.acm.org
Recent years have seen an exponential growth (+ 98% in 2022 wrt the previous year) of the
number of research articles in the few-shot learning field, which aims at training machine …

Improving fine-grained visual recognition in low data regimes via self-boosting attention mechanism

Y Shu, B Yu, H Xu, L Liu - European Conference on Computer Vision, 2022 - Springer
The challenge of fine-grained visual recognition often lies in discovering the key
discriminative regions. While such regions can be automatically identified from a large-scale …

Variational feature disentangling for fine-grained few-shot classification

J Xu, H Le, M Huang, SR Athar… - Proceedings of the …, 2021 - openaccess.thecvf.com
Data augmentation is an intuitive step towards solving the problem of few-shot classification.
However, ensuring both discriminability and diversity in the augmented samples is …

Multi-level second-order few-shot learning

H Zhang, H Li, P Koniusz - IEEE Transactions on Multimedia, 2022 - ieeexplore.ieee.org
We propose a Multi-level Second-order (MlSo) few-shot learning network for supervised or
unsupervised few-shot image classification and few-shot action recognition. We leverage so …