Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313303572> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4313303572 abstract "Vision transformers (ViTs) encoding an image as a sequence of patches bring new paradigms for semantic segmentation.We present an efficient framework of representation separation in local-patch level and global-region level for semantic segmentation with ViTs. It is targeted for the peculiar over-smoothness of ViTs in semantic segmentation, and therefore differs from current popular paradigms of context modeling and most existing related methods reinforcing the advantage of attention. We first deliver the decoupled two-pathway network in which another pathway enhances and passes down local-patch discrepancy complementary to global representations of transformers. We then propose the spatially adaptive separation module to obtain more separate deep representations and the discriminative cross-attention which yields more discriminative region representations through novel auxiliary supervisions. The proposed methods achieve some impressive results: 1) incorporated with large-scale plain ViTs, our methods achieve new state-of-the-art performances on five widely used benchmarks; 2) using masked pre-trained plain ViTs, we achieve 68.9% mIoU on Pascal Context, setting a new record; 3) pyramid ViTs integrated with the decoupled two-pathway network even surpass the well-designed high-resolution ViTs on Cityscapes; 4) the improved representations by our framework have favorable transferability in images with natural corruptions. The codes will be released publicly." @default.
- W4313303572 created "2023-01-06" @default.
- W4313303572 creator A5036684787 @default.
- W4313303572 creator A5044251375 @default.
- W4313303572 creator A5053786338 @default.
- W4313303572 creator A5062305704 @default.
- W4313303572 creator A5077953778 @default.
- W4313303572 date "2022-12-28" @default.
- W4313303572 modified "2023-09-23" @default.
- W4313303572 title "Representation Separation for Semantic Segmentation with Vision Transformers" @default.
- W4313303572 doi "https://doi.org/10.48550/arxiv.2212.13764" @default.
- W4313303572 hasPublicationYear "2022" @default.
- W4313303572 type Work @default.
- W4313303572 citedByCount "0" @default.
- W4313303572 crossrefType "posted-content" @default.
- W4313303572 hasAuthorship W4313303572A5036684787 @default.
- W4313303572 hasAuthorship W4313303572A5044251375 @default.
- W4313303572 hasAuthorship W4313303572A5053786338 @default.
- W4313303572 hasAuthorship W4313303572A5062305704 @default.
- W4313303572 hasAuthorship W4313303572A5077953778 @default.
- W4313303572 hasBestOaLocation W43133035721 @default.
- W4313303572 hasConcept C119599485 @default.
- W4313303572 hasConcept C127413603 @default.
- W4313303572 hasConcept C153180895 @default.
- W4313303572 hasConcept C154945302 @default.
- W4313303572 hasConcept C165801399 @default.
- W4313303572 hasConcept C199360897 @default.
- W4313303572 hasConcept C31972630 @default.
- W4313303572 hasConcept C41008148 @default.
- W4313303572 hasConcept C66322947 @default.
- W4313303572 hasConcept C75608658 @default.
- W4313303572 hasConcept C89600930 @default.
- W4313303572 hasConcept C97931131 @default.
- W4313303572 hasConceptScore W4313303572C119599485 @default.
- W4313303572 hasConceptScore W4313303572C127413603 @default.
- W4313303572 hasConceptScore W4313303572C153180895 @default.
- W4313303572 hasConceptScore W4313303572C154945302 @default.
- W4313303572 hasConceptScore W4313303572C165801399 @default.
- W4313303572 hasConceptScore W4313303572C199360897 @default.
- W4313303572 hasConceptScore W4313303572C31972630 @default.
- W4313303572 hasConceptScore W4313303572C41008148 @default.
- W4313303572 hasConceptScore W4313303572C66322947 @default.
- W4313303572 hasConceptScore W4313303572C75608658 @default.
- W4313303572 hasConceptScore W4313303572C89600930 @default.
- W4313303572 hasConceptScore W4313303572C97931131 @default.
- W4313303572 hasLocation W43133035721 @default.
- W4313303572 hasOpenAccess W4313303572 @default.
- W4313303572 hasPrimaryLocation W43133035721 @default.
- W4313303572 hasRelatedWork W1652783584 @default.
- W4313303572 hasRelatedWork W2024160000 @default.
- W4313303572 hasRelatedWork W2510758617 @default.
- W4313303572 hasRelatedWork W2799124825 @default.
- W4313303572 hasRelatedWork W2895616727 @default.
- W4313303572 hasRelatedWork W2965095255 @default.
- W4313303572 hasRelatedWork W74886973 @default.
- W4313303572 hasRelatedWork W82679236 @default.
- W4313303572 hasRelatedWork W2002704236 @default.
- W4313303572 hasRelatedWork W2073139667 @default.
- W4313303572 isParatext "false" @default.
- W4313303572 isRetracted "false" @default.
- W4313303572 workType "article" @default.