FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313153210> ?p ?o ?g. }

• W4313153210 abstract "Weakly-supervised semantic segmentation (WSSS) with image-level labels is an important and challenging task. Due to the high training efficiency, end-to-end solutions for WSSS have received increasing attention from the community. However, current methods are mainly based on convolutional neural networks and fail to explore the global information properly, thus usually resulting in incomplete object regions. In this paper, to address the aforementioned problem, we introduce Transformers, which naturally integrate global information, to generate more integral initial pseudo labels for end-to-end WSSS. Motivated by the inherent consistency between the self-attention in Transformers and the semantic affinity, we propose an Affinity from Attention (AFA) module to learn semantic affinity from the multi-head self-attention (MHSA) in Transformers. The learned affinity is then leveraged to refine the initial pseudo labels for segmentation. In addition, to efficiently derive reliable affinity labels for supervising AFA and ensure the local consistency of pseudo labels, we devise a Pixel-Adaptive Refinement module that incorporates low-level image appearance information to refine the pseudo labels. We perform extensive experiments and our method achieves 66.0% and 38.9% mIoU on the PASCAL VOC 2012 and MS COCO 2014 datasets, respectively, significantly outperforming recent end-to-end methods and several multi-stage competitors. Code is available at https://github.com/rulixiang/afa." @default.
• W4313153210 created "2023-01-06" @default.
• W4313153210 creator A5004758964 @default.
• W4313153210 creator A5074672983 @default.
• W4313153210 creator A5085309099 @default.
• W4313153210 creator A5090197479 @default.
• W4313153210 date "2022-06-01" @default.
• W4313153210 modified "2023-10-14" @default.
• W4313153210 title "Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers" @default.
• W4313153210 cites W1945608308 @default.
• W4313153210 cites W2031489346 @default.
• W4313153210 cites W2144794286 @default.
• W4313153210 cites W2194775991 @default.
• W4313153210 cites W2221898772 @default.
• W4313153210 cites W2337429362 @default.
• W4313153210 cites W2412782625 @default.
• W4313153210 cites W2558580397 @default.
• W4313153210 cites W2600144439 @default.
• W4313153210 cites W2739450375 @default.
• W4313153210 cites W2888340395 @default.
• W4313153210 cites W2962758679 @default.
• W4313153210 cites W2962867364 @default.
• W4313153210 cites W2963870605 @default.
• W4313153210 cites W2982093251 @default.
• W4313153210 cites W2996952120 @default.
• W4313153210 cites W3034373787 @default.
• W4313153210 cites W3034930876 @default.
• W4313153210 cites W3035703639 @default.
• W4313153210 cites W3100040694 @default.
• W4313153210 cites W3142837074 @default.
• W4313153210 cites W3164772195 @default.
• W4313153210 cites W3166286626 @default.
• W4313153210 cites W3169761117 @default.
• W4313153210 cites W3173957243 @default.
• W4313153210 cites W3175456851 @default.
• W4313153210 cites W3176692018 @default.
• W4313153210 cites W3176760243 @default.
• W4313153210 cites W3183732083 @default.
• W4313153210 cites W3190500189 @default.
• W4313153210 cites W3202299736 @default.
• W4313153210 cites W3202524699 @default.
• W4313153210 cites W3203036314 @default.
• W4313153210 cites W3207676276 @default.
• W4313153210 cites W4214520160 @default.
• W4313153210 cites W4214612132 @default.
• W4313153210 cites W4220950530 @default.
• W4313153210 doi "https://doi.org/10.1109/cvpr52688.2022.01634" @default.
• W4313153210 hasPublicationYear "2022" @default.
• W4313153210 type Work @default.
• W4313153210 citedByCount "27" @default.
• W4313153210 countsByYear W43131532102022 @default.
• W4313153210 countsByYear W43131532102023 @default.
• W4313153210 crossrefType "proceedings-article" @default.
• W4313153210 hasAuthorship W4313153210A5004758964 @default.
• W4313153210 hasAuthorship W4313153210A5074672983 @default.
• W4313153210 hasAuthorship W4313153210A5085309099 @default.
• W4313153210 hasAuthorship W4313153210A5090197479 @default.
• W4313153210 hasBestOaLocation W43131532102 @default.
• W4313153210 hasConcept C119857082 @default.
• W4313153210 hasConcept C121332964 @default.
• W4313153210 hasConcept C153180895 @default.
• W4313153210 hasConcept C154945302 @default.
• W4313153210 hasConcept C165801399 @default.
• W4313153210 hasConcept C199360897 @default.
• W4313153210 hasConcept C41008148 @default.
• W4313153210 hasConcept C62520636 @default.
• W4313153210 hasConcept C66322947 @default.
• W4313153210 hasConcept C74296488 @default.
• W4313153210 hasConcept C75608658 @default.
• W4313153210 hasConcept C81363708 @default.
• W4313153210 hasConcept C89600930 @default.
• W4313153210 hasConceptScore W4313153210C119857082 @default.
• W4313153210 hasConceptScore W4313153210C121332964 @default.
• W4313153210 hasConceptScore W4313153210C153180895 @default.
• W4313153210 hasConceptScore W4313153210C154945302 @default.
• W4313153210 hasConceptScore W4313153210C165801399 @default.
• W4313153210 hasConceptScore W4313153210C199360897 @default.
• W4313153210 hasConceptScore W4313153210C41008148 @default.
• W4313153210 hasConceptScore W4313153210C62520636 @default.
• W4313153210 hasConceptScore W4313153210C66322947 @default.
• W4313153210 hasConceptScore W4313153210C74296488 @default.
• W4313153210 hasConceptScore W4313153210C75608658 @default.
• W4313153210 hasConceptScore W4313153210C81363708 @default.
• W4313153210 hasConceptScore W4313153210C89600930 @default.
• W4313153210 hasFunder F4320321001 @default.
• W4313153210 hasLocation W43131532101 @default.
• W4313153210 hasLocation W43131532102 @default.
• W4313153210 hasOpenAccess W4313153210 @default.
• W4313153210 hasPrimaryLocation W43131532101 @default.
• W4313153210 hasRelatedWork W2424871898 @default.
• W4313153210 hasRelatedWork W2769435486 @default.
• W4313153210 hasRelatedWork W2952466432 @default.
• W4313153210 hasRelatedWork W3027997911 @default.
• W4313153210 hasRelatedWork W3093612317 @default.
• W4313153210 hasRelatedWork W3102253946 @default.
• W4313153210 hasRelatedWork W4200528772 @default.
• W4313153210 hasRelatedWork W4287776258 @default.
• W4313153210 hasRelatedWork W4297914674 @default.
• W4313153210 hasRelatedWork W4308191152 @default.
• W4313153210 isParatext "false" @default.

• next