Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385532471> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4385532471 abstract "Multi-label classification is a widely encountered problem in daily life, where an instance can be associated with multiple classes. In theory, this is a supervised learning method that requires a large amount of labeling. However, annotating data is time-consuming and may be infeasible for huge labeling spaces. In addition, label imbalance can limit the performance of multi-label classifiers, especially when some labels are missing. Therefore, it is meaningful to study how to train neural networks using partial labels. In this work, we address the issue of label imbalance and investigate how to train classifiers using partial labels in large labeling spaces. First, we introduce the pseudo-labeling technique, which allows commonly adopted networks to be applied in partially labeled settings without the need for additional complex structures. Then, we propose a novel loss function that leverages statistical information from existing datasets to effectively alleviate the label imbalance problem. In addition, we design a dynamic training scheme to reduce the dimension of the labeling space and further mitigate the imbalance. Finally, we conduct extensive experiments on some publicly available multi-label datasets such as COCO, NUS-WIDE, CUB, and Open Images to demonstrate the effectiveness of the proposed approach. The results show that our approach outperforms several state-of-the-art methods, and surprisingly, in some partial labeling settings, our approach even exceeds the methods trained with full labels." @default.
- W4385532471 created "2023-08-04" @default.
- W4385532471 creator A5006651636 @default.
- W4385532471 creator A5010642871 @default.
- W4385532471 creator A5039446470 @default.
- W4385532471 creator A5040961372 @default.
- W4385532471 creator A5049921697 @default.
- W4385532471 date "2023-05-23" @default.
- W4385532471 modified "2023-10-11" @default.
- W4385532471 title "Towards Imbalanced Large Scale Multi-label Classification with Partially Annotated Labels" @default.
- W4385532471 cites W2007972815 @default.
- W4385532471 cites W2102765684 @default.
- W4385532471 cites W2108598243 @default.
- W4385532471 cites W2146241755 @default.
- W4385532471 cites W2183341477 @default.
- W4385532471 cites W2549139847 @default.
- W4385532471 cites W2963351448 @default.
- W4385532471 cites W2969792713 @default.
- W4385532471 cites W3011722050 @default.
- W4385532471 cites W3095707208 @default.
- W4385532471 cites W3160262531 @default.
- W4385532471 cites W3165691894 @default.
- W4385532471 cites W4214673031 @default.
- W4385532471 cites W4244207479 @default.
- W4385532471 cites W4288083516 @default.
- W4385532471 cites W4361019813 @default.
- W4385532471 doi "https://doi.org/10.1109/sera57763.2023.10197667" @default.
- W4385532471 hasPublicationYear "2023" @default.
- W4385532471 type Work @default.
- W4385532471 citedByCount "0" @default.
- W4385532471 crossrefType "proceedings-article" @default.
- W4385532471 hasAuthorship W4385532471A5006651636 @default.
- W4385532471 hasAuthorship W4385532471A5010642871 @default.
- W4385532471 hasAuthorship W4385532471A5039446470 @default.
- W4385532471 hasAuthorship W4385532471A5040961372 @default.
- W4385532471 hasAuthorship W4385532471A5049921697 @default.
- W4385532471 hasBestOaLocation W43855324712 @default.
- W4385532471 hasConcept C119857082 @default.
- W4385532471 hasConcept C124101348 @default.
- W4385532471 hasConcept C134306372 @default.
- W4385532471 hasConcept C14036430 @default.
- W4385532471 hasConcept C151201525 @default.
- W4385532471 hasConcept C153180895 @default.
- W4385532471 hasConcept C154945302 @default.
- W4385532471 hasConcept C202444582 @default.
- W4385532471 hasConcept C2776482837 @default.
- W4385532471 hasConcept C33676613 @default.
- W4385532471 hasConcept C33923547 @default.
- W4385532471 hasConcept C41008148 @default.
- W4385532471 hasConcept C78458016 @default.
- W4385532471 hasConcept C86803240 @default.
- W4385532471 hasConceptScore W4385532471C119857082 @default.
- W4385532471 hasConceptScore W4385532471C124101348 @default.
- W4385532471 hasConceptScore W4385532471C134306372 @default.
- W4385532471 hasConceptScore W4385532471C14036430 @default.
- W4385532471 hasConceptScore W4385532471C151201525 @default.
- W4385532471 hasConceptScore W4385532471C153180895 @default.
- W4385532471 hasConceptScore W4385532471C154945302 @default.
- W4385532471 hasConceptScore W4385532471C202444582 @default.
- W4385532471 hasConceptScore W4385532471C2776482837 @default.
- W4385532471 hasConceptScore W4385532471C33676613 @default.
- W4385532471 hasConceptScore W4385532471C33923547 @default.
- W4385532471 hasConceptScore W4385532471C41008148 @default.
- W4385532471 hasConceptScore W4385532471C78458016 @default.
- W4385532471 hasConceptScore W4385532471C86803240 @default.
- W4385532471 hasLocation W43855324711 @default.
- W4385532471 hasLocation W43855324712 @default.
- W4385532471 hasOpenAccess W4385532471 @default.
- W4385532471 hasPrimaryLocation W43855324711 @default.
- W4385532471 hasRelatedWork W2912288872 @default.
- W4385532471 hasRelatedWork W2961085424 @default.
- W4385532471 hasRelatedWork W3046775127 @default.
- W4385532471 hasRelatedWork W3170094116 @default.
- W4385532471 hasRelatedWork W4205958290 @default.
- W4385532471 hasRelatedWork W4285260836 @default.
- W4385532471 hasRelatedWork W4286629047 @default.
- W4385532471 hasRelatedWork W4306321456 @default.
- W4385532471 hasRelatedWork W4306674287 @default.
- W4385532471 hasRelatedWork W4224009465 @default.
- W4385532471 isParatext "false" @default.
- W4385532471 isRetracted "false" @default.
- W4385532471 workType "article" @default.