Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387322610> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4387322610 abstract "The problem of missing modalities is both critical and non-trivial to be handled in multi-modal models. It is common for multi-modal tasks that certain modalities contribute more compared to other modalities, and if those important modalities are missing, the model performance drops significantly. Such fact remains unexplored by current multi-modal approaches that recover the representation from missing modalities by feature reconstruction or blind feature aggregation from other modalities, instead of extracting useful information from the best performing modalities. In this paper, we propose a Learnable Cross-modal Knowledge Distillation (LCKD) model to adaptively identify important modalities and distil knowledge from them to help other modalities from the cross-modal perspective for solving the missing modality issue. Our approach introduces a teacher election procedure to select the most ``qualified'' teachers based on their single modality performance on certain tasks. Then, cross-modal knowledge distillation is performed between teacher and student modalities for each task to push the model parameters to a point that is beneficial for all tasks. Hence, even if the teacher modalities for certain tasks are missing during testing, the available student modalities can accomplish the task well enough based on the learned knowledge from their automatically elected teacher modalities. Experiments on the Brain Tumour Segmentation Dataset 2018 (BraTS2018) shows that LCKD outperforms other methods by a considerable margin, improving the state-of-the-art performance by 3.61% for enhancing tumour, 5.99% for tumour core, and 3.76% for whole tumour in terms of segmentation Dice score." @default.
- W4387322610 created "2023-10-04" @default.
- W4387322610 creator A5029215323 @default.
- W4387322610 creator A5036455193 @default.
- W4387322610 creator A5052220949 @default.
- W4387322610 creator A5052912720 @default.
- W4387322610 creator A5058617327 @default.
- W4387322610 creator A5079344414 @default.
- W4387322610 date "2023-10-02" @default.
- W4387322610 modified "2023-10-06" @default.
- W4387322610 title "Learnable Cross-modal Knowledge Distillation for Multi-modal Learning with Missing Modality" @default.
- W4387322610 doi "https://doi.org/10.48550/arxiv.2310.01035" @default.
- W4387322610 hasPublicationYear "2023" @default.
- W4387322610 type Work @default.
- W4387322610 citedByCount "0" @default.
- W4387322610 crossrefType "posted-content" @default.
- W4387322610 hasAuthorship W4387322610A5029215323 @default.
- W4387322610 hasAuthorship W4387322610A5036455193 @default.
- W4387322610 hasAuthorship W4387322610A5052220949 @default.
- W4387322610 hasAuthorship W4387322610A5052912720 @default.
- W4387322610 hasAuthorship W4387322610A5058617327 @default.
- W4387322610 hasAuthorship W4387322610A5079344414 @default.
- W4387322610 hasBestOaLocation W43873226101 @default.
- W4387322610 hasConcept C119857082 @default.
- W4387322610 hasConcept C127413603 @default.
- W4387322610 hasConcept C138885662 @default.
- W4387322610 hasConcept C144024400 @default.
- W4387322610 hasConcept C153180895 @default.
- W4387322610 hasConcept C154945302 @default.
- W4387322610 hasConcept C17744445 @default.
- W4387322610 hasConcept C185592680 @default.
- W4387322610 hasConcept C188027245 @default.
- W4387322610 hasConcept C199539241 @default.
- W4387322610 hasConcept C201995342 @default.
- W4387322610 hasConcept C204321447 @default.
- W4387322610 hasConcept C2776359362 @default.
- W4387322610 hasConcept C2776401178 @default.
- W4387322610 hasConcept C2779903281 @default.
- W4387322610 hasConcept C2780226545 @default.
- W4387322610 hasConcept C2780451532 @default.
- W4387322610 hasConcept C36289849 @default.
- W4387322610 hasConcept C41008148 @default.
- W4387322610 hasConcept C41895202 @default.
- W4387322610 hasConcept C71139939 @default.
- W4387322610 hasConcept C89600930 @default.
- W4387322610 hasConcept C9357733 @default.
- W4387322610 hasConcept C94625758 @default.
- W4387322610 hasConceptScore W4387322610C119857082 @default.
- W4387322610 hasConceptScore W4387322610C127413603 @default.
- W4387322610 hasConceptScore W4387322610C138885662 @default.
- W4387322610 hasConceptScore W4387322610C144024400 @default.
- W4387322610 hasConceptScore W4387322610C153180895 @default.
- W4387322610 hasConceptScore W4387322610C154945302 @default.
- W4387322610 hasConceptScore W4387322610C17744445 @default.
- W4387322610 hasConceptScore W4387322610C185592680 @default.
- W4387322610 hasConceptScore W4387322610C188027245 @default.
- W4387322610 hasConceptScore W4387322610C199539241 @default.
- W4387322610 hasConceptScore W4387322610C201995342 @default.
- W4387322610 hasConceptScore W4387322610C204321447 @default.
- W4387322610 hasConceptScore W4387322610C2776359362 @default.
- W4387322610 hasConceptScore W4387322610C2776401178 @default.
- W4387322610 hasConceptScore W4387322610C2779903281 @default.
- W4387322610 hasConceptScore W4387322610C2780226545 @default.
- W4387322610 hasConceptScore W4387322610C2780451532 @default.
- W4387322610 hasConceptScore W4387322610C36289849 @default.
- W4387322610 hasConceptScore W4387322610C41008148 @default.
- W4387322610 hasConceptScore W4387322610C41895202 @default.
- W4387322610 hasConceptScore W4387322610C71139939 @default.
- W4387322610 hasConceptScore W4387322610C89600930 @default.
- W4387322610 hasConceptScore W4387322610C9357733 @default.
- W4387322610 hasConceptScore W4387322610C94625758 @default.
- W4387322610 hasLocation W43873226101 @default.
- W4387322610 hasOpenAccess W4387322610 @default.
- W4387322610 hasPrimaryLocation W43873226101 @default.
- W4387322610 hasRelatedWork W2004831463 @default.
- W4387322610 hasRelatedWork W2110287964 @default.
- W4387322610 hasRelatedWork W2383394264 @default.
- W4387322610 hasRelatedWork W3125968744 @default.
- W4387322610 hasRelatedWork W4224266612 @default.
- W4387322610 hasRelatedWork W4293261942 @default.
- W4387322610 hasRelatedWork W4307407935 @default.
- W4387322610 hasRelatedWork W4320153225 @default.
- W4387322610 hasRelatedWork W73545470 @default.
- W4387322610 hasRelatedWork W649759291 @default.
- W4387322610 isParatext "false" @default.
- W4387322610 isRetracted "false" @default.
- W4387322610 workType "article" @default.