Matches in SemOpenAlex for { <https://semopenalex.org/work/W3184223816> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W3184223816 abstract "One of the main challenges of applying deep learning for robotics is the difficulty of efficiently adapting to new tasks while still maintaining the same performance on previous tasks. The problem of incrementally learning new tasks commonly struggles with catastrophic forgetting in which the previous knowledge is lost.Class-incremental learning for semantic segmentation, addresses this problem in which we want to learn new semantic classes without having access to labeled data for previously learned classes. This is a problem in industry, where few pre-trained models and open datasets matches exactly the requisites. In these cases it is both expensive and labour intensive to collect an entirely new fully-labeled dataset. Instead, collecting a smaller dataset and only labeling the new classes is much more efficient in terms of data collection.In this paper we present the class-incremental learning problem for semantic segmentation, we discuss related work in terms of the more thoroughly studied classification task and experimentally validate the current state-of-the-art for semantic segmentation. This lays the foundation as we discuss some of the problems that still needs to be investigated and improved upon in order to reach a new state-of-the-art for class-incremental semantic segmentation." @default.
- W3184223816 created "2021-08-02" @default.
- W3184223816 creator A5042087981 @default.
- W3184223816 creator A5044139676 @default.
- W3184223816 creator A5059060359 @default.
- W3184223816 date "2021-06-14" @default.
- W3184223816 modified "2023-09-26" @default.
- W3184223816 title "Class-Incremental Learning for Semantic Segmentation - A study" @default.
- W3184223816 cites W1821462560 @default.
- W3184223816 cites W2473930607 @default.
- W3184223816 cites W2560647685 @default.
- W3184223816 cites W2630837129 @default.
- W3184223816 cites W2765407302 @default.
- W3184223816 cites W2939137134 @default.
- W3184223816 cites W2963073398 @default.
- W3184223816 cites W2963588172 @default.
- W3184223816 cites W2964189064 @default.
- W3184223816 cites W2982701845 @default.
- W3184223816 cites W3013325675 @default.
- W3184223816 cites W3034435444 @default.
- W3184223816 cites W3034856281 @default.
- W3184223816 cites W3035501943 @default.
- W3184223816 cites W3043271475 @default.
- W3184223816 cites W3100156920 @default.
- W3184223816 doi "https://doi.org/10.1109/sais53221.2021.9483955" @default.
- W3184223816 hasPublicationYear "2021" @default.
- W3184223816 type Work @default.
- W3184223816 sameAs 3184223816 @default.
- W3184223816 citedByCount "0" @default.
- W3184223816 crossrefType "proceedings-article" @default.
- W3184223816 hasAuthorship W3184223816A5042087981 @default.
- W3184223816 hasAuthorship W3184223816A5044139676 @default.
- W3184223816 hasAuthorship W3184223816A5059060359 @default.
- W3184223816 hasConcept C11413529 @default.
- W3184223816 hasConcept C119857082 @default.
- W3184223816 hasConcept C138885662 @default.
- W3184223816 hasConcept C154945302 @default.
- W3184223816 hasConcept C162324750 @default.
- W3184223816 hasConcept C184337299 @default.
- W3184223816 hasConcept C187736073 @default.
- W3184223816 hasConcept C199360897 @default.
- W3184223816 hasConcept C204321447 @default.
- W3184223816 hasConcept C2777212361 @default.
- W3184223816 hasConcept C2780451532 @default.
- W3184223816 hasConcept C2780735816 @default.
- W3184223816 hasConcept C41008148 @default.
- W3184223816 hasConcept C41895202 @default.
- W3184223816 hasConcept C48103436 @default.
- W3184223816 hasConcept C7149132 @default.
- W3184223816 hasConcept C89600930 @default.
- W3184223816 hasConceptScore W3184223816C11413529 @default.
- W3184223816 hasConceptScore W3184223816C119857082 @default.
- W3184223816 hasConceptScore W3184223816C138885662 @default.
- W3184223816 hasConceptScore W3184223816C154945302 @default.
- W3184223816 hasConceptScore W3184223816C162324750 @default.
- W3184223816 hasConceptScore W3184223816C184337299 @default.
- W3184223816 hasConceptScore W3184223816C187736073 @default.
- W3184223816 hasConceptScore W3184223816C199360897 @default.
- W3184223816 hasConceptScore W3184223816C204321447 @default.
- W3184223816 hasConceptScore W3184223816C2777212361 @default.
- W3184223816 hasConceptScore W3184223816C2780451532 @default.
- W3184223816 hasConceptScore W3184223816C2780735816 @default.
- W3184223816 hasConceptScore W3184223816C41008148 @default.
- W3184223816 hasConceptScore W3184223816C41895202 @default.
- W3184223816 hasConceptScore W3184223816C48103436 @default.
- W3184223816 hasConceptScore W3184223816C7149132 @default.
- W3184223816 hasConceptScore W3184223816C89600930 @default.
- W3184223816 hasFunder F4320321030 @default.
- W3184223816 hasLocation W31842238161 @default.
- W3184223816 hasOpenAccess W3184223816 @default.
- W3184223816 hasPrimaryLocation W31842238161 @default.
- W3184223816 hasRelatedWork W2081647779 @default.
- W3184223816 hasRelatedWork W3088215962 @default.
- W3184223816 hasRelatedWork W3107474891 @default.
- W3184223816 hasRelatedWork W3126776133 @default.
- W3184223816 hasRelatedWork W3185852197 @default.
- W3184223816 hasRelatedWork W3186262193 @default.
- W3184223816 hasRelatedWork W4225699316 @default.
- W3184223816 hasRelatedWork W4287234591 @default.
- W3184223816 hasRelatedWork W4309613512 @default.
- W3184223816 hasRelatedWork W4312120628 @default.
- W3184223816 isParatext "false" @default.
- W3184223816 isRetracted "false" @default.
- W3184223816 magId "3184223816" @default.
- W3184223816 workType "article" @default.