Improving Few-shot Learning by Spatially-aware Matching and CrossTransformer

Zhang, Hongguang; Torr, Philip H. S.; Koniusz, Piotr

doi:10.1007/978-3-031-26348-4_1

Cited by 1 publication

(2 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead, they train a typical classification network with two blocks: the feature extractor and the classification head. Many FSL models combine backbone with classification head [19,42,48,49,55], detection head [56][57][58], localization head [30] or detection head [15]. We focus on designing the inference stage and improving its performance in transductive and semi-supervised setting.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

EASE: Unsupervised Discriminant Subspace Learning for Transductive Few-Shot Learning

Zhu

Koniusz

2022

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Few-shot learning (FSL) is popular due to its ability to adapt to novel classes. Compared with inductive few-shot learning, transductive models typically perform better as they leverage all samples of the query set. The two existing classes of methods, prototype-based and graph-based, have the disadvantages of inaccurate prototype estimation and sub-optimal graph construction with kernel functions, respectively. In this paper, we propose a novel prototypebased label propagation to solve these issues. Specifically, our graph construction is based on the relation between prototypes and samples rather than between samples. As prototypes are being updated, the graph changes. We also estimate the label of each prototype instead of considering a prototype be the class centre. On mini-ImageNet, tiered-ImageNet, CIFAR-FS and CUB datasets, we show the proposed method outperforms other state-of-the-art methods in transductive FSL and semi-supervised FSL when some unlabeled data accompanies the novel few-shot task.

show abstract

Section: Related Workmentioning

confidence: 99%

“…mini-ImageNet. This dataset [73,77] is widely used in few-shot classification [65,66,71,72,75,76,80]. It contains 100 randomly chosen classes from ImageNet [74].…”

Section: Datasetsmentioning

confidence: 99%

EASE: Unsupervised Discriminant Subspace Learning for Transductive Few-Shot Learning

Zhu

Koniusz

2022

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

show abstract

Improving Few-shot Learning by Spatially-aware Matching and CrossTransformer

Cited by 1 publication

References 39 publications

EASE: Unsupervised Discriminant Subspace Learning for Transductive Few-Shot Learning

EASE: Unsupervised Discriminant Subspace Learning for Transductive Few-Shot Learning

Contact Info

Product

Resources

About