Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382459155> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4382459155 endingPage "1745" @default.
- W4382459155 startingPage "1737" @default.
- W4382459155 abstract "Multi-scale features from backbone networks have been widely applied to recover object details in segmentation tasks. Generally, the multi-level features are fused in a certain manner for further pixel-level dense prediction. Whereas, the spatial structure information is not fully explored, that is similar nearby pixels can be used to complement each other. In this paper, we investigate a progressive neighborhood aggregation (PNA) framework to refine the semantic segmentation prediction, resulting in an end-to-end solution that can perform the coarse prediction and refinement in a unified network. Specifically, we first present a neighborhood aggregation module, the neighborhood similarity matrices for each pixel are estimated on multi-scale features, which are further used to progressively aggregate the high-level feature for recovering the spatial structure. In addition, to further integrate the high-resolution details into the aggregated feature, we apply a self-aggregation module on the low-level features to emphasize important semantic information for complementing losing spatial details. Extensive experiments on five segmentation datasets, including Pascal VOC 2012, CityScapes, COCO-Stuff 10k, DeepGlobe, and Trans10k, demonstrate that the proposed framework can be cascaded into existing segmentation models providing consistent improvements. In particular, our method achieves new state-of-the-art performances on two challenging datasets, DeepGlobe and Trans10k. The code is available at https://github.com/liutinglt/PNA." @default.
- W4382459155 created "2023-06-29" @default.
- W4382459155 creator A5028235866 @default.
- W4382459155 creator A5057382261 @default.
- W4382459155 creator A5087043856 @default.
- W4382459155 date "2023-06-26" @default.
- W4382459155 modified "2023-10-12" @default.
- W4382459155 title "Progressive Neighborhood Aggregation for Semantic Segmentation Refinement" @default.
- W4382459155 doi "https://doi.org/10.1609/aaai.v37i2.25262" @default.
- W4382459155 hasPublicationYear "2023" @default.
- W4382459155 type Work @default.
- W4382459155 citedByCount "0" @default.
- W4382459155 crossrefType "journal-article" @default.
- W4382459155 hasAuthorship W4382459155A5028235866 @default.
- W4382459155 hasAuthorship W4382459155A5057382261 @default.
- W4382459155 hasAuthorship W4382459155A5087043856 @default.
- W4382459155 hasBestOaLocation W43824591551 @default.
- W4382459155 hasConcept C104317684 @default.
- W4382459155 hasConcept C112313634 @default.
- W4382459155 hasConcept C124101348 @default.
- W4382459155 hasConcept C127716648 @default.
- W4382459155 hasConcept C138885662 @default.
- W4382459155 hasConcept C153180895 @default.
- W4382459155 hasConcept C154945302 @default.
- W4382459155 hasConcept C159985019 @default.
- W4382459155 hasConcept C160633673 @default.
- W4382459155 hasConcept C177264268 @default.
- W4382459155 hasConcept C185592680 @default.
- W4382459155 hasConcept C188082640 @default.
- W4382459155 hasConcept C192562407 @default.
- W4382459155 hasConcept C199360897 @default.
- W4382459155 hasConcept C2776401178 @default.
- W4382459155 hasConcept C2776760102 @default.
- W4382459155 hasConcept C41008148 @default.
- W4382459155 hasConcept C41895202 @default.
- W4382459155 hasConcept C4679612 @default.
- W4382459155 hasConcept C55493867 @default.
- W4382459155 hasConcept C75608658 @default.
- W4382459155 hasConcept C89600930 @default.
- W4382459155 hasConceptScore W4382459155C104317684 @default.
- W4382459155 hasConceptScore W4382459155C112313634 @default.
- W4382459155 hasConceptScore W4382459155C124101348 @default.
- W4382459155 hasConceptScore W4382459155C127716648 @default.
- W4382459155 hasConceptScore W4382459155C138885662 @default.
- W4382459155 hasConceptScore W4382459155C153180895 @default.
- W4382459155 hasConceptScore W4382459155C154945302 @default.
- W4382459155 hasConceptScore W4382459155C159985019 @default.
- W4382459155 hasConceptScore W4382459155C160633673 @default.
- W4382459155 hasConceptScore W4382459155C177264268 @default.
- W4382459155 hasConceptScore W4382459155C185592680 @default.
- W4382459155 hasConceptScore W4382459155C188082640 @default.
- W4382459155 hasConceptScore W4382459155C192562407 @default.
- W4382459155 hasConceptScore W4382459155C199360897 @default.
- W4382459155 hasConceptScore W4382459155C2776401178 @default.
- W4382459155 hasConceptScore W4382459155C2776760102 @default.
- W4382459155 hasConceptScore W4382459155C41008148 @default.
- W4382459155 hasConceptScore W4382459155C41895202 @default.
- W4382459155 hasConceptScore W4382459155C4679612 @default.
- W4382459155 hasConceptScore W4382459155C55493867 @default.
- W4382459155 hasConceptScore W4382459155C75608658 @default.
- W4382459155 hasConceptScore W4382459155C89600930 @default.
- W4382459155 hasIssue "2" @default.
- W4382459155 hasLocation W43824591551 @default.
- W4382459155 hasOpenAccess W4382459155 @default.
- W4382459155 hasPrimaryLocation W43824591551 @default.
- W4382459155 hasRelatedWork W2090093270 @default.
- W4382459155 hasRelatedWork W2136485282 @default.
- W4382459155 hasRelatedWork W2532775738 @default.
- W4382459155 hasRelatedWork W2546871836 @default.
- W4382459155 hasRelatedWork W2799124825 @default.
- W4382459155 hasRelatedWork W2907667403 @default.
- W4382459155 hasRelatedWork W3105240641 @default.
- W4382459155 hasRelatedWork W3160284275 @default.
- W4382459155 hasRelatedWork W4288328879 @default.
- W4382459155 hasRelatedWork W4304730814 @default.
- W4382459155 hasVolume "37" @default.
- W4382459155 isParatext "false" @default.
- W4382459155 isRetracted "false" @default.
- W4382459155 workType "article" @default.