Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226058394> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4226058394 abstract "Recent progress has shown that large-scale pre-training using contrastive image-text pairs can be a promising alternative for high-quality visual representation learning from natural language supervision. Benefiting from a broader source of supervision, this new paradigm exhibits impressive transferability to downstream classification tasks and datasets. However, the problem of transferring the knowledge learned from image-text pairs to more complex dense prediction tasks has barely been visited. In this work, we present a new framework for dense prediction by implicitly and explicitly leveraging the pre-trained knowledge from CLIP. Specifically, we convert the original image-text matching problem in CLIP to a pixel-text matching problem and use the pixel-text score maps to guide the learning of dense prediction models. By further using the contextual information from the image to prompt the language model, we are able to facilitate our model to better exploit the pretrained knowledge. Our method is model-agnostic, which can be applied to arbitrary dense prediction systems and various pre-trained visual backbones including both CLIP models and ImageNet pre-trained models. Extensive experiments demonstrate the superior performance of our methods on semantic segmentation, object detection, and instance segmentation tasks. Code is available at https://github.com/raoyongming/DenseCLIP." @default.
- W4226058394 created "2022-05-05" @default.
- W4226058394 creator A5010357390 @default.
- W4226058394 creator A5036569726 @default.
- W4226058394 creator A5040497930 @default.
- W4226058394 creator A5044985818 @default.
- W4226058394 creator A5077076810 @default.
- W4226058394 creator A5082694832 @default.
- W4226058394 creator A5088257057 @default.
- W4226058394 creator A5090079801 @default.
- W4226058394 date "2022-06-01" @default.
- W4226058394 modified "2023-10-16" @default.
- W4226058394 title "DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting" @default.
- W4226058394 doi "https://doi.org/10.1109/cvpr52688.2022.01755" @default.
- W4226058394 hasPublicationYear "2022" @default.
- W4226058394 type Work @default.
- W4226058394 citedByCount "66" @default.
- W4226058394 countsByYear W42260583942022 @default.
- W4226058394 countsByYear W42260583942023 @default.
- W4226058394 crossrefType "proceedings-article" @default.
- W4226058394 hasAuthorship W4226058394A5010357390 @default.
- W4226058394 hasAuthorship W4226058394A5036569726 @default.
- W4226058394 hasAuthorship W4226058394A5040497930 @default.
- W4226058394 hasAuthorship W4226058394A5044985818 @default.
- W4226058394 hasAuthorship W4226058394A5077076810 @default.
- W4226058394 hasAuthorship W4226058394A5082694832 @default.
- W4226058394 hasAuthorship W4226058394A5088257057 @default.
- W4226058394 hasAuthorship W4226058394A5090079801 @default.
- W4226058394 hasBestOaLocation W42260583942 @default.
- W4226058394 hasConcept C105795698 @default.
- W4226058394 hasConcept C119857082 @default.
- W4226058394 hasConcept C151730666 @default.
- W4226058394 hasConcept C153180895 @default.
- W4226058394 hasConcept C154945302 @default.
- W4226058394 hasConcept C160633673 @default.
- W4226058394 hasConcept C165064840 @default.
- W4226058394 hasConcept C165696696 @default.
- W4226058394 hasConcept C195324797 @default.
- W4226058394 hasConcept C204321447 @default.
- W4226058394 hasConcept C2779343474 @default.
- W4226058394 hasConcept C33923547 @default.
- W4226058394 hasConcept C38652104 @default.
- W4226058394 hasConcept C41008148 @default.
- W4226058394 hasConcept C86803240 @default.
- W4226058394 hasConcept C89600930 @default.
- W4226058394 hasConceptScore W4226058394C105795698 @default.
- W4226058394 hasConceptScore W4226058394C119857082 @default.
- W4226058394 hasConceptScore W4226058394C151730666 @default.
- W4226058394 hasConceptScore W4226058394C153180895 @default.
- W4226058394 hasConceptScore W4226058394C154945302 @default.
- W4226058394 hasConceptScore W4226058394C160633673 @default.
- W4226058394 hasConceptScore W4226058394C165064840 @default.
- W4226058394 hasConceptScore W4226058394C165696696 @default.
- W4226058394 hasConceptScore W4226058394C195324797 @default.
- W4226058394 hasConceptScore W4226058394C204321447 @default.
- W4226058394 hasConceptScore W4226058394C2779343474 @default.
- W4226058394 hasConceptScore W4226058394C33923547 @default.
- W4226058394 hasConceptScore W4226058394C38652104 @default.
- W4226058394 hasConceptScore W4226058394C41008148 @default.
- W4226058394 hasConceptScore W4226058394C86803240 @default.
- W4226058394 hasConceptScore W4226058394C89600930 @default.
- W4226058394 hasFunder F4320321001 @default.
- W4226058394 hasLocation W42260583941 @default.
- W4226058394 hasLocation W42260583942 @default.
- W4226058394 hasOpenAccess W4226058394 @default.
- W4226058394 hasPrimaryLocation W42260583941 @default.
- W4226058394 hasRelatedWork W1496222301 @default.
- W4226058394 hasRelatedWork W1590307681 @default.
- W4226058394 hasRelatedWork W2296488620 @default.
- W4226058394 hasRelatedWork W2353836703 @default.
- W4226058394 hasRelatedWork W2358353312 @default.
- W4226058394 hasRelatedWork W3207760230 @default.
- W4226058394 hasRelatedWork W41015297 @default.
- W4226058394 hasRelatedWork W4280645561 @default.
- W4226058394 hasRelatedWork W4285370786 @default.
- W4226058394 hasRelatedWork W4312814274 @default.
- W4226058394 isParatext "false" @default.
- W4226058394 isRetracted "false" @default.
- W4226058394 workType "article" @default.