English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Few-shot image classification requires the classifier to robustly cope withunseen classes even if there are only a few samples for each class. Recentadvances benefit from the meta-learning process where episodic tasks are formedto train a model that can adapt to class change. However, these task sareindependent to each other and existing works mainly rely on limited samples ofindividual support set in a single meta task. This strategy leads to severemeta shift issues across multiple tasks, meaning the learned prototypes orclass descriptors are not stable as each task only involves their own supportset. To avoid this problem, we propose a concise Semantic RegularizationNetworkto learn a common semantic space under the framework of meta-learning. In thisspace, all class descriptors can be regularized by the learned semantic basis,which can effectively solve the meta shift problem. The key is to train a classencoder and decoder structure that can encode the sample embedding featuresinto the semantic domain with trained semantic basis, and generate a morestable and general class descriptor from the decoder. We evaluate our work byextensive comparisons with previous methods on three benchmark datasets(MiniImageNet, TieredImageNet, and CUB). The results show that the semanticregularization module improves performance by 4%-7% over the baseline method,and achieves competitive results over the current state-of-the-art models.

Semantic Regularization: Improve Few-shot Image Classification by Reducing Meta Shift