Matches in SemOpenAlex for { <https://semopenalex.org/work/W4324107137> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4324107137 abstract "The click-based interactive segmentation aims to extract the object of interest from an image with the guidance of user clicks. Recent work has achieved great overall performance by employing the segmentation from the previous output. However, in most state-of-the-art approaches, 1) the inference stage involves inflexible heuristic rules and a separate refinement model; and 2) the training cannot balance the number of user clicks and model performance. To address the challenges, we propose a click-based and mask-guided interactive image segmentation framework containing three novel components: Cascade-Forward Refinement (CFR), Iterative Click Loss (ICL), and SUEM image augmentation. The proposed ICL allows model training to improve segmentation and reduce user interactions simultaneously. The CFR offers a unified inference framework to generate segmentation results in a coarse-to-fine manner. The proposed SUEM augmentation is a comprehensive way to create large and diverse training sets for interactive image segmentation. Extensive experiments demonstrate the state-of-the-art performance of the proposed approach on five public datasets. Remarkably, our model achieves an average of 2.9 and 7.5 clicks of NoC@95 on the Berkeley and DAVIS sets, respectively, improving by 33.2% and 15.5% over the previous state-of-the-art results. The code and trained model are available at https://github.com/TitorX/CFR-ICL-Interactive-Segmentation." @default.
- W4324107137 created "2023-03-14" @default.
- W4324107137 creator A5007010423 @default.
- W4324107137 creator A5038590199 @default.
- W4324107137 creator A5071938296 @default.
- W4324107137 creator A5080652935 @default.
- W4324107137 creator A5089962019 @default.
- W4324107137 date "2023-03-09" @default.
- W4324107137 modified "2023-10-16" @default.
- W4324107137 title "CFR-ICL: Cascade-Forward Refinement with Iterative Click Loss for Interactive Image Segmentation" @default.
- W4324107137 doi "https://doi.org/10.48550/arxiv.2303.05620" @default.
- W4324107137 hasPublicationYear "2023" @default.
- W4324107137 type Work @default.
- W4324107137 citedByCount "0" @default.
- W4324107137 crossrefType "posted-content" @default.
- W4324107137 hasAuthorship W4324107137A5007010423 @default.
- W4324107137 hasAuthorship W4324107137A5038590199 @default.
- W4324107137 hasAuthorship W4324107137A5071938296 @default.
- W4324107137 hasAuthorship W4324107137A5080652935 @default.
- W4324107137 hasAuthorship W4324107137A5089962019 @default.
- W4324107137 hasBestOaLocation W43241071371 @default.
- W4324107137 hasConcept C115961682 @default.
- W4324107137 hasConcept C124504099 @default.
- W4324107137 hasConcept C154945302 @default.
- W4324107137 hasConcept C173801870 @default.
- W4324107137 hasConcept C177264268 @default.
- W4324107137 hasConcept C185592680 @default.
- W4324107137 hasConcept C199360897 @default.
- W4324107137 hasConcept C2776214188 @default.
- W4324107137 hasConcept C2776760102 @default.
- W4324107137 hasConcept C2781238097 @default.
- W4324107137 hasConcept C31972630 @default.
- W4324107137 hasConcept C34146451 @default.
- W4324107137 hasConcept C41008148 @default.
- W4324107137 hasConcept C43126263 @default.
- W4324107137 hasConcept C43617362 @default.
- W4324107137 hasConcept C89600930 @default.
- W4324107137 hasConceptScore W4324107137C115961682 @default.
- W4324107137 hasConceptScore W4324107137C124504099 @default.
- W4324107137 hasConceptScore W4324107137C154945302 @default.
- W4324107137 hasConceptScore W4324107137C173801870 @default.
- W4324107137 hasConceptScore W4324107137C177264268 @default.
- W4324107137 hasConceptScore W4324107137C185592680 @default.
- W4324107137 hasConceptScore W4324107137C199360897 @default.
- W4324107137 hasConceptScore W4324107137C2776214188 @default.
- W4324107137 hasConceptScore W4324107137C2776760102 @default.
- W4324107137 hasConceptScore W4324107137C2781238097 @default.
- W4324107137 hasConceptScore W4324107137C31972630 @default.
- W4324107137 hasConceptScore W4324107137C34146451 @default.
- W4324107137 hasConceptScore W4324107137C41008148 @default.
- W4324107137 hasConceptScore W4324107137C43126263 @default.
- W4324107137 hasConceptScore W4324107137C43617362 @default.
- W4324107137 hasConceptScore W4324107137C89600930 @default.
- W4324107137 hasLocation W43241071371 @default.
- W4324107137 hasOpenAccess W4324107137 @default.
- W4324107137 hasPrimaryLocation W43241071371 @default.
- W4324107137 hasRelatedWork W1631910785 @default.
- W4324107137 hasRelatedWork W1669643531 @default.
- W4324107137 hasRelatedWork W1963494852 @default.
- W4324107137 hasRelatedWork W2004370856 @default.
- W4324107137 hasRelatedWork W2019566805 @default.
- W4324107137 hasRelatedWork W2026019026 @default.
- W4324107137 hasRelatedWork W2101128524 @default.
- W4324107137 hasRelatedWork W2122581818 @default.
- W4324107137 hasRelatedWork W2383464976 @default.
- W4324107137 hasRelatedWork W1967061043 @default.
- W4324107137 isParatext "false" @default.
- W4324107137 isRetracted "false" @default.
- W4324107137 workType "article" @default.