Acknowledging the Unknown for Multi-label Learning with Single Positive Labels
Refereed conference paper presented and published in conference proceedings
Full Text
Digital Object Identifier (DOI) DOI for CUHK Users |
Altmetrics Information
.
Other information
AbstractDue to the difficulty of collecting exhaustive multi-label annotations, multi-label datasets often contain partial labels. We consider an extreme of this weakly supervised learning problem, called single positive multi-label learning (SPML), where each multi-label training image has only one positive label. Traditionally, all unannotated labels are assumed as negative labels in SPML, which introduces false negative labels and causes model training to be dominated by assumed negative labels. In this work, we choose to treat all unannotated labels from an alternative perspective, i.e. acknowledging they are unknown. Hence, we propose entropy-maximization (EM) loss to attain a special gradient regime for providing proper supervision signals. Moreover, we propose asymmetric pseudo-labeling (APL), which adopts asymmetric-tolerance strategies and a self-paced procedure, to cooperate with EM loss and then provide more precise supervision. Experiments show that our method significantly improves performance and achieves state-of-the-art results on all four benchmarks. Code is available at https://github.com/Correr-Zhou/SPML-AckTheUnknown.
All Author(s) ListZhou DH, Chen PF, Wang Q, Chen GY, Heng PA
Name of ConferenceECCV
Start Date of Conference25/10/2022
End Date of Conference27/10/2022
Place of ConferenceTel-Aviv
Country/Region of ConferenceIsrael
Title of PublicationCOMPUTER VISION, ECCV 2022, PT XXIV
Year2022
Volume Number13684
PublisherSPRINGER INTERNATIONAL PUBLISHING AG, GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND
Pages423 - 440
ISSN0302-9743
LanguagesEnglish-United Kingdom
KeywordsWeakly supervised learning, Single positive multi-label learning, Entropy maximization, Pseudo-labeling
Web of Science Subject CategoriesComputer Science, Artificial Intelligence;Imaging Science & Photographic Technology;Computer Science;Imaging Science & Photographic Technology
