Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381929644> ?p ?o ?g. }
- W4381929644 abstract "Abstract In this paper, we extend Open-set Semantic Segmentation (OSS) into a new image segmentation task called Generalized Open-set Semantic Segmentation (GOSS). Previously, with well-known OSS, the intelligent agents only detect unknown regions without further processing, limiting their perception capacity of the environment. It stands to reason that further analysis of the detected unknown pixels would be beneficial for agents’ decision-making. Therefore, we propose GOSS, which holistically unifies the abilities of two well-defined segmentation tasks, i.e. OSS and generic segmentation. Specifically, GOSS classifies pixels as belonging to known classes, and clusters (or groups) of pixels of unknown class are labelled as such. We propose a metric that balances the pixel classification and clustering aspects to evaluate this newly expanded task. Moreover, we build benchmark tests on existing datasets and propose neural architectures as baselines. Our experiments on multiple benchmarks demonstrate the effectiveness of our baselines. Code is made available at https://github.com/JHome1/GOSS_Segmentor ." @default.
- W4381929644 created "2023-06-25" @default.
- W4381929644 creator A5003554707 @default.
- W4381929644 creator A5021790939 @default.
- W4381929644 creator A5031463327 @default.
- W4381929644 creator A5034960969 @default.
- W4381929644 creator A5057904986 @default.
- W4381929644 creator A5060335798 @default.
- W4381929644 creator A5089491113 @default.
- W4381929644 date "2023-06-23" @default.
- W4381929644 modified "2023-10-18" @default.
- W4381929644 title "GOSS: towards generalized open-set semantic segmentation" @default.
- W4381929644 cites W1528789833 @default.
- W4381929644 cites W1861492603 @default.
- W4381929644 cites W1903029394 @default.
- W4381929644 cites W1905829557 @default.
- W4381929644 cites W1966716734 @default.
- W4381929644 cites W1976526581 @default.
- W4381929644 cites W1999478155 @default.
- W4381929644 cites W2031489346 @default.
- W4381929644 cites W2033403400 @default.
- W4381929644 cites W2067191022 @default.
- W4381929644 cites W2083931353 @default.
- W4381929644 cites W2108598243 @default.
- W4381929644 cites W2110158442 @default.
- W4381929644 cites W2119823327 @default.
- W4381929644 cites W2121947440 @default.
- W4381929644 cites W2125637308 @default.
- W4381929644 cites W2141729166 @default.
- W4381929644 cites W2150134683 @default.
- W4381929644 cites W2158698691 @default.
- W4381929644 cites W2194775991 @default.
- W4381929644 cites W2299400169 @default.
- W4381929644 cites W2340897893 @default.
- W4381929644 cites W2412782625 @default.
- W4381929644 cites W2561196672 @default.
- W4381929644 cites W2593584281 @default.
- W4381929644 cites W2737258237 @default.
- W4381929644 cites W2749895778 @default.
- W4381929644 cites W2807830984 @default.
- W4381929644 cites W2910628332 @default.
- W4381929644 cites W2950921159 @default.
- W4381929644 cites W2963321359 @default.
- W4381929644 cites W2963498646 @default.
- W4381929644 cites W2963921921 @default.
- W4381929644 cites W2964309882 @default.
- W4381929644 cites W2974038048 @default.
- W4381929644 cites W2981786146 @default.
- W4381929644 cites W2982106100 @default.
- W4381929644 cites W2999219213 @default.
- W4381929644 cites W3009436130 @default.
- W4381929644 cites W3034512663 @default.
- W4381929644 cites W3035326800 @default.
- W4381929644 cites W3099193570 @default.
- W4381929644 cites W3110437118 @default.
- W4381929644 cites W3112906266 @default.
- W4381929644 cites W3122412340 @default.
- W4381929644 cites W3170019900 @default.
- W4381929644 cites W3170841864 @default.
- W4381929644 cites W3176640650 @default.
- W4381929644 cites W3176709420 @default.
- W4381929644 cites W3177266689 @default.
- W4381929644 cites W3201876338 @default.
- W4381929644 cites W3204557602 @default.
- W4381929644 cites W4205172069 @default.
- W4381929644 cites W4214530306 @default.
- W4381929644 cites W4214756262 @default.
- W4381929644 cites W4281666638 @default.
- W4381929644 cites W4312815172 @default.
- W4381929644 cites W55377555 @default.
- W4381929644 doi "https://doi.org/10.1007/s00371-023-02925-8" @default.
- W4381929644 hasPublicationYear "2023" @default.
- W4381929644 type Work @default.
- W4381929644 citedByCount "0" @default.
- W4381929644 crossrefType "journal-article" @default.
- W4381929644 hasAuthorship W4381929644A5003554707 @default.
- W4381929644 hasAuthorship W4381929644A5021790939 @default.
- W4381929644 hasAuthorship W4381929644A5031463327 @default.
- W4381929644 hasAuthorship W4381929644A5034960969 @default.
- W4381929644 hasAuthorship W4381929644A5057904986 @default.
- W4381929644 hasAuthorship W4381929644A5060335798 @default.
- W4381929644 hasAuthorship W4381929644A5089491113 @default.
- W4381929644 hasBestOaLocation W43819296441 @default.
- W4381929644 hasConcept C119857082 @default.
- W4381929644 hasConcept C124504099 @default.
- W4381929644 hasConcept C13280743 @default.
- W4381929644 hasConcept C153180895 @default.
- W4381929644 hasConcept C154945302 @default.
- W4381929644 hasConcept C160633673 @default.
- W4381929644 hasConcept C162324750 @default.
- W4381929644 hasConcept C176217482 @default.
- W4381929644 hasConcept C177264268 @default.
- W4381929644 hasConcept C185798385 @default.
- W4381929644 hasConcept C187736073 @default.
- W4381929644 hasConcept C199360897 @default.
- W4381929644 hasConcept C205649164 @default.
- W4381929644 hasConcept C21547014 @default.
- W4381929644 hasConcept C2776760102 @default.
- W4381929644 hasConcept C2777212361 @default.
- W4381929644 hasConcept C2780451532 @default.