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

Long-tailed multi-label visual recognition (LTML) task is a highlychallenging task due to the label co-occurrence and imbalanced datadistribution. In this work, we propose a unified framework for LTML, namelyprompt tuning with class-specific embedding loss (LMPT), capturing the semanticfeature interactions between categories by combining text and image modalitydata and improving the performance synchronously on both head and tail classes.Specifically, LMPT introduces the embedding loss function with class-aware softmargin and re-weighting to learn class-specific contexts with the benefit oftextual descriptions (captions), which could help establish semanticrelationships between classes, especially between the head and tail classes.Furthermore, taking into account the class imbalance, the distribution-balancedloss is adopted as the classification loss function to further improve theperformance on the tail classes without compromising head classes. Extensiveexperiments are conducted on VOC-LT and COCO-LT datasets, which demonstratesthat the proposed method significantly surpasses the previous state-of-the-artmethods and zero-shot CLIP in LTML. Our codes are fully available at\url{https://github.com/richard-peng-xia/LMPT}.

LMPT: Prompt Tuning with Class-Specific Embedding Loss for Long-tailed Multi-Label Visual Recognition