Long-tail recognition via compositional knowledge transfer

Sarah Parisot, Pedro M Esperança, Steven McDonagh, Tamas J Madarasz, Yongxin Yang, Zhenguo Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

In this work, we introduce a novel strategy for long-tail recognition that addresses the tail classes’ few-shot problem via training-free knowledge transfer. Our objective is to transfer knowledge acquired from information-rich common classes to semantically similar, and yet data-hungry, rare classes in order to obtain stronger tail class representations. We leverage the fact that class prototypes and learned cosine classifiers provide two different, complementary representations of class cluster centres in feature space, and use an attention mechanism to select and recompose learned classifier features from common classes to obtain higher quality rare class representations. Our knowledge transfer process is training free, reducing overfitting risks, and can afford continual extension of classifiers to new classes. Experiments show that our approach can achieve significant performance boosts on rare classes while maintaining robust common class performance, outperforming directly comparable state-of-the-art models
Original languageUndefined/Unknown
Title of host publication2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Number of pages10
Publication statusPublished - 27 Sept 2022
EventIEEE/CVF Conference on Computer Vision and Pattern Recognition 2022
- New Orleans, United States
Duration: 19 Jun 202224 Jun 2022

Publication series

NameConference on Computer Vision and Pattern Recognition (CVPR)
ISSN (Electronic)2575-7075


ConferenceIEEE/CVF Conference on Computer Vision and Pattern Recognition 2022
Abbreviated titleCVPR 2022
Country/TerritoryUnited States
CityNew Orleans
Internet address

Cite this