Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204111873> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3204111873 abstract "Stream-based active learning (AL) is an efficient training data collection method, and it is used to reduce human annotation cost required in machine learning. However, it is difficult to say that the human cost is low enough because most previous studies have assumed that an oracle is a human with domain knowledge. In this study, we propose a method to replace a part of the oracle’s work in stream-based AL by self-training with weak labeling using a robot arm. A camera attached to a robot arm takes a series of image data related to a streamed object, which should have the same label. We use this information as a weak label to connect a pseudo-label (estimated class label) and a target instance. Our method selects two data from a series of image data; high confidence data for correcting pseudo-labels and low confidence data for improving the performance of the classifier. We paired a pseudo-label provided to high confidence data with a target instance (low confidence data). By using this technique, we mitigate the inefficiency in self-training, that is, difficulty in creating pseudo-labeled training data with a high impact on the target classifier. In the experiments, we employed the proposed method in the classification task of objects on a belt conveyor. We evaluated the performance against human cost on multiple scenarios considering the temporal variation of data. The proposed method achieves the same or better performance as the conventional methods while reducing human cost." @default.
- W3204111873 created "2021-10-11" @default.
- W3204111873 creator A5027074375 @default.
- W3204111873 creator A5042578984 @default.
- W3204111873 creator A5042849965 @default.
- W3204111873 creator A5061054269 @default.
- W3204111873 date "2021-09-27" @default.
- W3204111873 modified "2023-09-27" @default.
- W3204111873 title "Annotation Cost Reduction of Stream-based Active Learning by Automated Weak Labeling using a Robot Arm" @default.
- W3204111873 cites W104184427 @default.
- W3204111873 cites W1566499617 @default.
- W3204111873 cites W1731081199 @default.
- W3204111873 cites W2048679005 @default.
- W3204111873 cites W2127816222 @default.
- W3204111873 cites W2163605009 @default.
- W3204111873 cites W2194775991 @default.
- W3204111873 cites W2594718649 @default.
- W3204111873 cites W2605991684 @default.
- W3204111873 cites W2776054962 @default.
- W3204111873 cites W2903158431 @default.
- W3204111873 cites W2904849495 @default.
- W3204111873 cites W2919358988 @default.
- W3204111873 cites W2949098821 @default.
- W3204111873 cites W2956371155 @default.
- W3204111873 cites W2962804657 @default.
- W3204111873 cites W2963233928 @default.
- W3204111873 cites W2963775347 @default.
- W3204111873 cites W2964040467 @default.
- W3204111873 cites W2964073328 @default.
- W3204111873 cites W2964151081 @default.
- W3204111873 cites W2964189064 @default.
- W3204111873 cites W2986514296 @default.
- W3204111873 cites W2991542429 @default.
- W3204111873 cites W3012178173 @default.
- W3204111873 cites W3025091470 @default.
- W3204111873 doi "https://doi.org/10.1109/iros51168.2021.9636355" @default.
- W3204111873 hasPublicationYear "2021" @default.
- W3204111873 type Work @default.
- W3204111873 sameAs 3204111873 @default.
- W3204111873 citedByCount "0" @default.
- W3204111873 crossrefType "proceedings-article" @default.
- W3204111873 hasAuthorship W3204111873A5027074375 @default.
- W3204111873 hasAuthorship W3204111873A5042578984 @default.
- W3204111873 hasAuthorship W3204111873A5042849965 @default.
- W3204111873 hasAuthorship W3204111873A5061054269 @default.
- W3204111873 hasBestOaLocation W32041118732 @default.
- W3204111873 hasConcept C115903868 @default.
- W3204111873 hasConcept C119857082 @default.
- W3204111873 hasConcept C124101348 @default.
- W3204111873 hasConcept C150415221 @default.
- W3204111873 hasConcept C153180895 @default.
- W3204111873 hasConcept C154945302 @default.
- W3204111873 hasConcept C31972630 @default.
- W3204111873 hasConcept C41008148 @default.
- W3204111873 hasConcept C55166926 @default.
- W3204111873 hasConcept C90509273 @default.
- W3204111873 hasConcept C95623464 @default.
- W3204111873 hasConceptScore W3204111873C115903868 @default.
- W3204111873 hasConceptScore W3204111873C119857082 @default.
- W3204111873 hasConceptScore W3204111873C124101348 @default.
- W3204111873 hasConceptScore W3204111873C150415221 @default.
- W3204111873 hasConceptScore W3204111873C153180895 @default.
- W3204111873 hasConceptScore W3204111873C154945302 @default.
- W3204111873 hasConceptScore W3204111873C31972630 @default.
- W3204111873 hasConceptScore W3204111873C41008148 @default.
- W3204111873 hasConceptScore W3204111873C55166926 @default.
- W3204111873 hasConceptScore W3204111873C90509273 @default.
- W3204111873 hasConceptScore W3204111873C95623464 @default.
- W3204111873 hasFunder F4320338246 @default.
- W3204111873 hasLocation W32041118731 @default.
- W3204111873 hasLocation W32041118732 @default.
- W3204111873 hasOpenAccess W3204111873 @default.
- W3204111873 hasPrimaryLocation W32041118731 @default.
- W3204111873 hasRelatedWork W2061090284 @default.
- W3204111873 hasRelatedWork W2061662597 @default.
- W3204111873 hasRelatedWork W2125579716 @default.
- W3204111873 hasRelatedWork W2147818368 @default.
- W3204111873 hasRelatedWork W2198681394 @default.
- W3204111873 hasRelatedWork W2474469336 @default.
- W3204111873 hasRelatedWork W2684384989 @default.
- W3204111873 hasRelatedWork W2961085424 @default.
- W3204111873 hasRelatedWork W67682705 @default.
- W3204111873 hasRelatedWork W3158004940 @default.
- W3204111873 isParatext "false" @default.
- W3204111873 isRetracted "false" @default.
- W3204111873 magId "3204111873" @default.
- W3204111873 workType "article" @default.