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 learning (FSL) aims to learn a classifier that can be easily adaptedto accommodate new tasks not seen during training, given only a few examples.To handle the limited-data problem in few-shot regimes, recent methods tend tocollectively use a set of local features to densely represent an image insteadof using a mixed global feature. They generally explore a unidirectionalquery-to-support paradigm in FSL, e.g., find the nearest/optimal supportfeature for each query feature and aggregate these local matches for a jointclassification. In this paper, we propose a new method Mutual CentralizedLearning (MCL) to fully affiliate the two disjoint sets of dense features in abidirectional paradigm. We associate each local feature with a particle thatcan bidirectionally random walk in a discrete feature space by theaffiliations. To estimate the class probability, we propose the features'accessibility that measures the expected number of visits to the supportfeatures of that class in a Markov process. We relate our method to learning acentrality on an affiliation network and demonstrate its capability to beplugged in existing methods by highlighting centralized local features.Experiments show that our method achieves the state-of-the-art on bothminiImageNet and tieredImageNet.

Learning to Affiliate: Mutual Centralized Learning for Few-shot Classification