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

Learning fine-grained embeddings from coarse labels is a challenging task dueto limited label granularity supervision, i.e., lacking the detaileddistinctions required for fine-grained tasks. The task becomes even moredemanding when attempting few-shot fine-grained recognition, which holdspractical significance in various applications. To address these challenges, wepropose a novel method that embeds visual embeddings into a hyperbolic spaceand enhances their discriminative ability with a hierarchical cosine marginsmanner. Specifically, the hyperbolic space offers distinct advantages,including the ability to capture hierarchical relationships and increasedexpressive power, which favors modeling fine-grained objects. Based on thehyperbolic space, we further enforce relatively large/small similarity marginsbetween coarse/fine classes, respectively, yielding the so-called hierarchicalcosine margins manner. While enforcing similarity margins in the regularEuclidean space has become popular for deep embedding learning, applying it tothe hyperbolic space is non-trivial and validating the benefit forcoarse-to-fine generalization is valuable. Extensive experiments conducted onfive benchmark datasets showcase the effectiveness of our proposed method,yielding state-of-the-art results surpassing competing methods.

Hyperbolic Space with Hierarchical Margin Boosts Fine-Grained Learning from Coarse Labels