Matches in SemOpenAlex for { <https://semopenalex.org/work/W3088431063> ?p ?o ?g. }
- W3088431063 endingPage "7703" @default.
- W3088431063 startingPage "7689" @default.
- W3088431063 abstract "Zero-shot learning (ZSL) has been actively studied for image classification tasks to relieve the burden of annotating image labels. Interestingly, the semantic segmentation task requires more labor-intensive pixel-wise annotation, but zero-shot semantic segmentation has not attracted extensive research interest. Thus, we focus on zero-shot semantic segmentation that aims to segment unseen objects with only category-level semantic representations provided for unseen categories. In this article, we propose a novel context-aware feature generation network (CaGNet) that can synthesize context-aware pixel-wise visual features for unseen categories based on category-level semantic representations and pixel-wise contextual information. The synthesized features are used to fine-tune the classifier to enable segmenting of unseen objects. Furthermore, we extend pixel-wise feature generation and fine-tuning to patch-wise feature generation and fine-tuning, which additionally considers the interpixel relationship. Experimental results on Pascal-VOC, Pascal-context, and COCO-stuff show that our method significantly outperforms the existing zero-shot semantic segmentation methods." @default.
- W3088431063 created "2020-10-01" @default.
- W3088431063 creator A5032618817 @default.
- W3088431063 creator A5048045743 @default.
- W3088431063 creator A5069553088 @default.
- W3088431063 creator A5070191030 @default.
- W3088431063 creator A5077967587 @default.
- W3088431063 date "2023-10-01" @default.
- W3088431063 modified "2023-10-16" @default.
- W3088431063 title "From Pixel to Patch: Synthesize Context-Aware Features for Zero-Shot Semantic Segmentation" @default.
- W3088431063 cites W1903029394 @default.
- W3088431063 cites W2013101727 @default.
- W3088431063 cites W2037227137 @default.
- W3088431063 cites W2117539524 @default.
- W3088431063 cites W2125215748 @default.
- W3088431063 cites W2127944900 @default.
- W3088431063 cites W2128532956 @default.
- W3088431063 cites W2141350700 @default.
- W3088431063 cites W2144794286 @default.
- W3088431063 cites W2171061940 @default.
- W3088431063 cites W2194775991 @default.
- W3088431063 cites W2221898772 @default.
- W3088431063 cites W2337429362 @default.
- W3088431063 cites W2412782625 @default.
- W3088431063 cites W2435696002 @default.
- W3088431063 cites W2552414813 @default.
- W3088431063 cites W2560023338 @default.
- W3088431063 cites W2561196672 @default.
- W3088431063 cites W2563705555 @default.
- W3088431063 cites W2585521554 @default.
- W3088431063 cites W2593414223 @default.
- W3088431063 cites W2599626790 @default.
- W3088431063 cites W2609698233 @default.
- W3088431063 cites W2793404847 @default.
- W3088431063 cites W2798441115 @default.
- W3088431063 cites W2887567284 @default.
- W3088431063 cites W2891932073 @default.
- W3088431063 cites W2896435145 @default.
- W3088431063 cites W2897510511 @default.
- W3088431063 cites W2902651581 @default.
- W3088431063 cites W2924476266 @default.
- W3088431063 cites W2924485953 @default.
- W3088431063 cites W2955087950 @default.
- W3088431063 cites W2963073614 @default.
- W3088431063 cites W2963078159 @default.
- W3088431063 cites W2963253279 @default.
- W3088431063 cites W2963420272 @default.
- W3088431063 cites W2963470893 @default.
- W3088431063 cites W2963626623 @default.
- W3088431063 cites W2963728677 @default.
- W3088431063 cites W2963960318 @default.
- W3088431063 cites W2964024144 @default.
- W3088431063 cites W2965373098 @default.
- W3088431063 cites W2979571231 @default.
- W3088431063 cites W2981812367 @default.
- W3088431063 cites W2983850069 @default.
- W3088431063 cites W2994827984 @default.
- W3088431063 cites W3033361357 @default.
- W3088431063 cites W3033502887 @default.
- W3088431063 cites W3034730995 @default.
- W3088431063 cites W3035655772 @default.
- W3088431063 cites W3047385447 @default.
- W3088431063 cites W3086361745 @default.
- W3088431063 cites W3091264770 @default.
- W3088431063 cites W3099554308 @default.
- W3088431063 cites W3105765741 @default.
- W3088431063 cites W3106029750 @default.
- W3088431063 cites W3143107425 @default.
- W3088431063 doi "https://doi.org/10.1109/tnnls.2022.3145962" @default.
- W3088431063 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35143403" @default.
- W3088431063 hasPublicationYear "2023" @default.
- W3088431063 type Work @default.
- W3088431063 sameAs 3088431063 @default.
- W3088431063 citedByCount "3" @default.
- W3088431063 countsByYear W30884310632022 @default.
- W3088431063 countsByYear W30884310632023 @default.
- W3088431063 crossrefType "journal-article" @default.
- W3088431063 hasAuthorship W3088431063A5032618817 @default.
- W3088431063 hasAuthorship W3088431063A5048045743 @default.
- W3088431063 hasAuthorship W3088431063A5069553088 @default.
- W3088431063 hasAuthorship W3088431063A5070191030 @default.
- W3088431063 hasAuthorship W3088431063A5077967587 @default.
- W3088431063 hasBestOaLocation W30884310632 @default.
- W3088431063 hasConcept C125308379 @default.
- W3088431063 hasConcept C138885662 @default.
- W3088431063 hasConcept C144133560 @default.
- W3088431063 hasConcept C153180895 @default.
- W3088431063 hasConcept C154945302 @default.
- W3088431063 hasConcept C160633673 @default.
- W3088431063 hasConcept C162853370 @default.
- W3088431063 hasConcept C166957645 @default.
- W3088431063 hasConcept C178790620 @default.
- W3088431063 hasConcept C185592680 @default.
- W3088431063 hasConcept C199360897 @default.
- W3088431063 hasConcept C204321447 @default.
- W3088431063 hasConcept C205649164 @default.
- W3088431063 hasConcept C2776401178 @default.
- W3088431063 hasConcept C2778344882 @default.