Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386415485> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W4386415485 endingPage "17" @default.
- W4386415485 startingPage "1" @default.
- W4386415485 abstract "This paper concentrates on open-vocabulary semantic segmentation, where a well optimized model is able to segment arbitrary categories that appear in an image. To achieve this goal, we present a novel framework termed Side Adapter Network, or SAN for short. Our design principles are three-fold: 1) Recent large-scale vision-language models (e.g. CLIP) show promising open-vocabulary image classification capability; it is training-economized to adapt a pre-trained CLIP model to open-vocabulary semantic segmentation. 2) Our SAN model should be both lightweight and effective in order to reduce the inference cost-to achieve this, we fuse the CLIP model's intermediate features to enhance the representation capability of the SAN model, and drive the CLIP model to focus on the informative areas of an image with the aid of the attention biases predicted by a side adapter network. 3) Our approach should empower mainstream segmentation architectures to have the capability of open-vocabulary segmentation-we present P-SAN and R-SAN, to support widely adopted pixel-wise segmentation and region-wise segmentation, respectively. Experimentally, our approach achieves state-of-the-art performance on 5 commonly used benchmarks while having much less trainable parameters and GFLOPs. For instance, our R-SAN outperforms previous best method OvSeg by +2.3 averaged mIoU across all benchmarks while using only 6% of trainable parameters and less than 1% of GFLOPs. In addition, we also conduct a comprehensive analysis of the open-vocabulary semantic segmentation datasets and verify the feasibility of transferring a well optimzied R-SAN model to video segmentation task. Code and models are available at <uri xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>https://github.com/MendelXu/SAN</uri> ." @default.
- W4386415485 created "2023-09-05" @default.
- W4386415485 creator A5004662803 @default.
- W4386415485 creator A5039363991 @default.
- W4386415485 creator A5084464680 @default.
- W4386415485 creator A5087428956 @default.
- W4386415485 creator A5090973869 @default.
- W4386415485 date "2023-01-01" @default.
- W4386415485 modified "2023-10-16" @default.
- W4386415485 title "SAN: Side Adapter Network for Open-vocabulary Semantic Segmentation" @default.
- W4386415485 doi "https://doi.org/10.1109/tpami.2023.3311618" @default.
- W4386415485 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37665708" @default.
- W4386415485 hasPublicationYear "2023" @default.
- W4386415485 type Work @default.
- W4386415485 citedByCount "0" @default.
- W4386415485 crossrefType "journal-article" @default.
- W4386415485 hasAuthorship W4386415485A5004662803 @default.
- W4386415485 hasAuthorship W4386415485A5039363991 @default.
- W4386415485 hasAuthorship W4386415485A5084464680 @default.
- W4386415485 hasAuthorship W4386415485A5087428956 @default.
- W4386415485 hasAuthorship W4386415485A5090973869 @default.
- W4386415485 hasConcept C111919701 @default.
- W4386415485 hasConcept C119857082 @default.
- W4386415485 hasConcept C124504099 @default.
- W4386415485 hasConcept C138885662 @default.
- W4386415485 hasConcept C153180895 @default.
- W4386415485 hasConcept C154945302 @default.
- W4386415485 hasConcept C177284502 @default.
- W4386415485 hasConcept C204321447 @default.
- W4386415485 hasConcept C2776214188 @default.
- W4386415485 hasConcept C2777601683 @default.
- W4386415485 hasConcept C31972630 @default.
- W4386415485 hasConcept C41008148 @default.
- W4386415485 hasConcept C41895202 @default.
- W4386415485 hasConcept C89600930 @default.
- W4386415485 hasConceptScore W4386415485C111919701 @default.
- W4386415485 hasConceptScore W4386415485C119857082 @default.
- W4386415485 hasConceptScore W4386415485C124504099 @default.
- W4386415485 hasConceptScore W4386415485C138885662 @default.
- W4386415485 hasConceptScore W4386415485C153180895 @default.
- W4386415485 hasConceptScore W4386415485C154945302 @default.
- W4386415485 hasConceptScore W4386415485C177284502 @default.
- W4386415485 hasConceptScore W4386415485C204321447 @default.
- W4386415485 hasConceptScore W4386415485C2776214188 @default.
- W4386415485 hasConceptScore W4386415485C2777601683 @default.
- W4386415485 hasConceptScore W4386415485C31972630 @default.
- W4386415485 hasConceptScore W4386415485C41008148 @default.
- W4386415485 hasConceptScore W4386415485C41895202 @default.
- W4386415485 hasConceptScore W4386415485C89600930 @default.
- W4386415485 hasLocation W43864154851 @default.
- W4386415485 hasLocation W43864154852 @default.
- W4386415485 hasOpenAccess W4386415485 @default.
- W4386415485 hasPrimaryLocation W43864154851 @default.
- W4386415485 hasRelatedWork W1669643531 @default.
- W4386415485 hasRelatedWork W1982826852 @default.
- W4386415485 hasRelatedWork W2005437358 @default.
- W4386415485 hasRelatedWork W2008656436 @default.
- W4386415485 hasRelatedWork W2023558673 @default.
- W4386415485 hasRelatedWork W2110230079 @default.
- W4386415485 hasRelatedWork W2134924024 @default.
- W4386415485 hasRelatedWork W2517104666 @default.
- W4386415485 hasRelatedWork W2613186388 @default.
- W4386415485 hasRelatedWork W1967061043 @default.
- W4386415485 isParatext "false" @default.
- W4386415485 isRetracted "false" @default.
- W4386415485 workType "article" @default.