Matches in SemOpenAlex for { <https://semopenalex.org/work/W2988677032> ?p ?o ?g. }
- W2988677032 abstract "To minimize the annotation costs associated with the training of semantic segmentation models, researchers have extensively investigated weakly-supervised segmentation approaches. In the current weakly-supervised segmentation methods, the most widely adopted approach is based on visualization. However, the visualization results are not generally equal to semantic segmentation. Therefore, to perform accurate semantic segmentation under the weakly supervised condition, it is necessary to consider the mapping functions that convert the visualization results into semantic segmentation. For such mapping functions, the conditional random field and iterative re-training using the outputs of a segmentation model are usually used. However, these methods do not always guarantee improvements in accuracy; therefore, if we apply these mapping functions iteratively multiple times, eventually the accuracy will not improve or will decrease. In this paper, to make the most of such mapping functions, we assume that the results of the mapping function include noise, and we improve the accuracy by removing noise. To achieve our aim, we propose the self-supervised difference detection module, which estimates noise from the results of the mapping functions by predicting the difference between the segmentation masks before and after the mapping. We verified the effectiveness of the proposed method by performing experiments on the PASCAL Visual Object Classes 2012 dataset, and we achieved 64.9% in the val set and 65.5% in the test set. Both of the results become new state-of-the-art under the same setting of weakly supervised semantic segmentation." @default.
- W2988677032 created "2019-11-22" @default.
- W2988677032 creator A5051127663 @default.
- W2988677032 creator A5054600485 @default.
- W2988677032 date "2019-11-04" @default.
- W2988677032 modified "2023-10-16" @default.
- W2988677032 title "Self-Supervised Difference Detection for Weakly-Supervised Semantic Segmentation" @default.
- W2988677032 cites W1507506748 @default.
- W2988677032 cites W1529410181 @default.
- W2988677032 cites W1783315696 @default.
- W2988677032 cites W1849277567 @default.
- W2988677032 cites W1903029394 @default.
- W2988677032 cites W1945608308 @default.
- W2988677032 cites W1991367009 @default.
- W2988677032 cites W2141200610 @default.
- W2988677032 cites W2161185676 @default.
- W2988677032 cites W2161236525 @default.
- W2988677032 cites W2161381512 @default.
- W2988677032 cites W2295537950 @default.
- W2988677032 cites W2306289963 @default.
- W2988677032 cites W2310700882 @default.
- W2988677032 cites W2503388974 @default.
- W2988677032 cites W2516803306 @default.
- W2988677032 cites W2520746254 @default.
- W2988677032 cites W2585521554 @default.
- W2988677032 cites W2585747585 @default.
- W2988677032 cites W2600144439 @default.
- W2988677032 cites W2606129492 @default.
- W2988677032 cites W2739450375 @default.
- W2988677032 cites W2798376494 @default.
- W2988677032 cites W2798683932 @default.
- W2988677032 cites W2799124825 @default.
- W2988677032 cites W2894666165 @default.
- W2988677032 cites W2950468556 @default.
- W2988677032 cites W2962758679 @default.
- W2988677032 cites W2962841641 @default.
- W2988677032 cites W2962851944 @default.
- W2988677032 cites W2962867364 @default.
- W2988677032 cites W2963263347 @default.
- W2988677032 cites W2963346885 @default.
- W2988677032 cites W2963606198 @default.
- W2988677032 cites W2963670239 @default.
- W2988677032 cites W2963697527 @default.
- W2988677032 cites W2963977581 @default.
- W2988677032 cites W2982093251 @default.
- W2988677032 cites W2985407551 @default.
- W2988677032 cites W2991366018 @default.
- W2988677032 cites W2991633843 @default.
- W2988677032 cites W3005164579 @default.
- W2988677032 cites W343636949 @default.
- W2988677032 cites W611457968 @default.
- W2988677032 doi "https://doi.org/10.48550/arxiv.1911.01370" @default.
- W2988677032 hasPublicationYear "2019" @default.
- W2988677032 type Work @default.
- W2988677032 sameAs 2988677032 @default.
- W2988677032 citedByCount "0" @default.
- W2988677032 crossrefType "posted-content" @default.
- W2988677032 hasAuthorship W2988677032A5051127663 @default.
- W2988677032 hasAuthorship W2988677032A5054600485 @default.
- W2988677032 hasBestOaLocation W29886770321 @default.
- W2988677032 hasConcept C115961682 @default.
- W2988677032 hasConcept C119857082 @default.
- W2988677032 hasConcept C124504099 @default.
- W2988677032 hasConcept C136389625 @default.
- W2988677032 hasConcept C152565575 @default.
- W2988677032 hasConcept C153180895 @default.
- W2988677032 hasConcept C154945302 @default.
- W2988677032 hasConcept C177264268 @default.
- W2988677032 hasConcept C199360897 @default.
- W2988677032 hasConcept C25694479 @default.
- W2988677032 hasConcept C2776321320 @default.
- W2988677032 hasConcept C36464697 @default.
- W2988677032 hasConcept C41008148 @default.
- W2988677032 hasConcept C50644808 @default.
- W2988677032 hasConcept C65885262 @default.
- W2988677032 hasConcept C75608658 @default.
- W2988677032 hasConcept C89600930 @default.
- W2988677032 hasConcept C99498987 @default.
- W2988677032 hasConceptScore W2988677032C115961682 @default.
- W2988677032 hasConceptScore W2988677032C119857082 @default.
- W2988677032 hasConceptScore W2988677032C124504099 @default.
- W2988677032 hasConceptScore W2988677032C136389625 @default.
- W2988677032 hasConceptScore W2988677032C152565575 @default.
- W2988677032 hasConceptScore W2988677032C153180895 @default.
- W2988677032 hasConceptScore W2988677032C154945302 @default.
- W2988677032 hasConceptScore W2988677032C177264268 @default.
- W2988677032 hasConceptScore W2988677032C199360897 @default.
- W2988677032 hasConceptScore W2988677032C25694479 @default.
- W2988677032 hasConceptScore W2988677032C2776321320 @default.
- W2988677032 hasConceptScore W2988677032C36464697 @default.
- W2988677032 hasConceptScore W2988677032C41008148 @default.
- W2988677032 hasConceptScore W2988677032C50644808 @default.
- W2988677032 hasConceptScore W2988677032C65885262 @default.
- W2988677032 hasConceptScore W2988677032C75608658 @default.
- W2988677032 hasConceptScore W2988677032C89600930 @default.
- W2988677032 hasConceptScore W2988677032C99498987 @default.
- W2988677032 hasLocation W29886770321 @default.
- W2988677032 hasOpenAccess W2988677032 @default.
- W2988677032 hasPrimaryLocation W29886770321 @default.
- W2988677032 hasRelatedWork W1977295039 @default.