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

Recent deep metric learning (DML) methods typically leverage solely classlabels to keep positive samples far away from negative ones. However, this typeof method normally ignores the crucial knowledge hidden in the data (e.g.,intra-class information variation), which is harmful to the generalization ofthe trained model. To alleviate this problem, in this paper we propose OnlineBatch Diffusion-based Self-Distillation (OBD-SD) for DML. Specifically, wefirst propose a simple but effective Progressive Self-Distillation (PSD), whichdistills the knowledge progressively from the model itself during training. Thesoft distance targets achieved by PSD can present richer relational informationamong samples, which is beneficial for the diversity of embeddingrepresentations. Then, we extend PSD with an Online Batch Diffusion Process(OBDP), which is to capture the local geometric structure of manifolds in eachbatch, so that it can reveal the intrinsic relationships among samples in thebatch and produce better soft distance targets. Note that our OBDP is able torestore the insufficient manifold relationships obtained by the original PSDand achieve significant performance improvement. Our OBD-SD is a flexibleframework that can be integrated into state-of-the-art (SOTA) DML methods.Extensive experiments on various benchmarks, namely CUB200, CARS196, andStanford Online Products, demonstrate that our OBD-SD consistently improves theperformance of the existing DML methods on multiple datasets with negligibleadditional training time, achieving very competitive results. Code:\url{https://github.com/ZelongZeng/OBD-SD_Pytorch}

Self-distillation with Online Diffusion on Batch Manifolds Improves Deep Metric Learning