Matches in SemOpenAlex for { <https://semopenalex.org/work/W4323922018> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4323922018 abstract "Prompt learning has achieved great success in efficiently exploiting large-scale pre-trained models in natural language processing (NLP). It reformulates the downstream tasks as the generative pre-training ones, thus narrowing down the gap between them and improving the performance stably. However, when transferring it to the vision area, current visual prompt learning methods are all designed on discriminative pre-trained models, and there is also a lack of careful design to unify the forms of pre-training and downstream tasks. To explore prompt learning on the generative pre-trained visual model as well as keeping the task consistency, we propose Visual Prompt learning as masked visual Token Modeling (VPTM) to transform the downstream visual classification into the pre-trained masked visual token prediction. In addition, we develop the prototypical verbalizer for mapping the predicted visual token with implicit semantics to explicit downstream labels. To our best knowledge, VPTM is the first visual prompt method on the generative pre-trained visual model, and the first to achieve consistency between pre-training and downstream visual classification by task reformulation. Experiments show that VPTM outperforms other visual prompt methods and achieves excellent efficiency. Moreover, the task consistency of VPTM contributes to the robustness against prompt location, prompt length and prototype dimension, and could be deployed uniformly." @default.
- W4323922018 created "2023-03-12" @default.
- W4323922018 creator A5003421579 @default.
- W4323922018 creator A5007238584 @default.
- W4323922018 creator A5035574012 @default.
- W4323922018 creator A5035837633 @default.
- W4323922018 creator A5047455588 @default.
- W4323922018 creator A5087158377 @default.
- W4323922018 date "2023-03-08" @default.
- W4323922018 modified "2023-09-26" @default.
- W4323922018 title "Rethinking Visual Prompt Learning as Masked Visual Token Modeling" @default.
- W4323922018 doi "https://doi.org/10.48550/arxiv.2303.04998" @default.
- W4323922018 hasPublicationYear "2023" @default.
- W4323922018 type Work @default.
- W4323922018 citedByCount "0" @default.
- W4323922018 crossrefType "posted-content" @default.
- W4323922018 hasAuthorship W4323922018A5003421579 @default.
- W4323922018 hasAuthorship W4323922018A5007238584 @default.
- W4323922018 hasAuthorship W4323922018A5035574012 @default.
- W4323922018 hasAuthorship W4323922018A5035837633 @default.
- W4323922018 hasAuthorship W4323922018A5047455588 @default.
- W4323922018 hasAuthorship W4323922018A5087158377 @default.
- W4323922018 hasBestOaLocation W43239220181 @default.
- W4323922018 hasConcept C104317684 @default.
- W4323922018 hasConcept C119857082 @default.
- W4323922018 hasConcept C154945302 @default.
- W4323922018 hasConcept C162324750 @default.
- W4323922018 hasConcept C167966045 @default.
- W4323922018 hasConcept C185592680 @default.
- W4323922018 hasConcept C187736073 @default.
- W4323922018 hasConcept C21547014 @default.
- W4323922018 hasConcept C2776207758 @default.
- W4323922018 hasConcept C2776436953 @default.
- W4323922018 hasConcept C2780451532 @default.
- W4323922018 hasConcept C38652104 @default.
- W4323922018 hasConcept C39890363 @default.
- W4323922018 hasConcept C41008148 @default.
- W4323922018 hasConcept C48145219 @default.
- W4323922018 hasConcept C55493867 @default.
- W4323922018 hasConcept C63479239 @default.
- W4323922018 hasConcept C97931131 @default.
- W4323922018 hasConceptScore W4323922018C104317684 @default.
- W4323922018 hasConceptScore W4323922018C119857082 @default.
- W4323922018 hasConceptScore W4323922018C154945302 @default.
- W4323922018 hasConceptScore W4323922018C162324750 @default.
- W4323922018 hasConceptScore W4323922018C167966045 @default.
- W4323922018 hasConceptScore W4323922018C185592680 @default.
- W4323922018 hasConceptScore W4323922018C187736073 @default.
- W4323922018 hasConceptScore W4323922018C21547014 @default.
- W4323922018 hasConceptScore W4323922018C2776207758 @default.
- W4323922018 hasConceptScore W4323922018C2776436953 @default.
- W4323922018 hasConceptScore W4323922018C2780451532 @default.
- W4323922018 hasConceptScore W4323922018C38652104 @default.
- W4323922018 hasConceptScore W4323922018C39890363 @default.
- W4323922018 hasConceptScore W4323922018C41008148 @default.
- W4323922018 hasConceptScore W4323922018C48145219 @default.
- W4323922018 hasConceptScore W4323922018C55493867 @default.
- W4323922018 hasConceptScore W4323922018C63479239 @default.
- W4323922018 hasConceptScore W4323922018C97931131 @default.
- W4323922018 hasLocation W43239220181 @default.
- W4323922018 hasOpenAccess W4323922018 @default.
- W4323922018 hasPrimaryLocation W43239220181 @default.
- W4323922018 hasRelatedWork W2251149342 @default.
- W4323922018 hasRelatedWork W2294985537 @default.
- W4323922018 hasRelatedWork W2874782909 @default.
- W4323922018 hasRelatedWork W2898645116 @default.
- W4323922018 hasRelatedWork W2952072295 @default.
- W4323922018 hasRelatedWork W3113145805 @default.
- W4323922018 hasRelatedWork W3173547984 @default.
- W4323922018 hasRelatedWork W4287703692 @default.
- W4323922018 hasRelatedWork W4289760695 @default.
- W4323922018 hasRelatedWork W2310403681 @default.
- W4323922018 isParatext "false" @default.
- W4323922018 isRetracted "false" @default.
- W4323922018 workType "article" @default.