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

A family of loss functions built on pair-based computation have been proposedin the literature which provide a myriad of solutions for deep metric learning.In this paper, we provide a general weighting framework for understandingrecent pair-based loss functions. Our contributions are three-fold: (1) weestablish a General Pair Weighting (GPW) framework, which casts the samplingproblem of deep metric learning into a unified view of pair weighting throughgradient analysis, providing a powerful tool for understanding recentpair-based loss functions; (2) we show that with GPW, various existingpair-based methods can be compared and discussed comprehensively, with cleardifferences and key limitations identified; (3) we propose a new loss calledmulti-similarity loss (MS loss) under the GPW, which is implemented in twoiterative steps (i.e., mining and weighting). This allows it to fully considerthree similarities for pair weighting, providing a more principled approach forcollecting and weighting informative pairs. Finally, the proposed MS lossobtains new state-of-the-art performance on four image retrieval benchmarks,where it outperforms the most recent approaches, such asABE\cite{Kim_2018_ECCV} and HTL by a large margin: 60.6% to 65.7% on CUB200,and 80.9% to 88.0% on In-Shop Clothes Retrieval dataset at Recall@1. Code isavailable at https://github.com/MalongTech/research-ms-loss.

Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning