FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3022146783> ?p ?o ?g. }

• W3022146783 endingPage "2684" @default.
• W3022146783 startingPage "2684" @default.
• W3022146783 abstract "Traffic sign recognition is a classification problem that poses challenges for computer vision and machine learning algorithms. Although both computer vision and machine learning techniques have constantly been improved to solve this problem, the sudden rise in the number of unlabeled traffic signs has become even more challenging. Large data collation and labeling are tedious and expensive tasks that demand much time, expert knowledge, and fiscal resources to satisfy the hunger of deep neural networks. Aside from that, the problem of having unbalanced data also poses a greater challenge to computer vision and machine learning algorithms to achieve better performance. These problems raise the need to develop algorithms that can fully exploit a large amount of unlabeled data, use a small amount of labeled samples, and be robust to data imbalance to build an efficient and high-quality classifier. In this work, we propose a novel semi-supervised classification technique that is robust to small and unbalanced data. The framework integrates weakly-supervised learning and self-training with self-paced learning to generate attention maps to augment the training set and utilizes a novel pseudo-label generation and selection algorithm to generate and select pseudo-labeled samples. The method improves the performance by: (1) normalizing the class-wise confidence levels to prevent the model from ignoring hard-to-learn samples, thereby solving the imbalanced data problem; (2) jointly learning a model and optimizing pseudo-labels generated on unlabeled data; and (3) enlarging the training set to satisfy the hunger of deep learning models. Extensive evaluations on two public traffic sign recognition datasets demonstrate the effectiveness of the proposed technique and provide a potential solution for practical applications." @default.
• W3022146783 created "2020-05-13" @default.
• W3022146783 creator A5012354366 @default.
• W3022146783 creator A5016430669 @default.
• W3022146783 creator A5030022647 @default.
• W3022146783 creator A5041192515 @default.
• W3022146783 creator A5044010094 @default.
• W3022146783 date "2020-05-08" @default.
• W3022146783 modified "2023-09-23" @default.
• W3022146783 title "Robust Semi-Supervised Traffic Sign Recognition via Self-Training and Weakly-Supervised Learning" @default.
• W3022146783 cites W1977610018 @default.
• W3022146783 cites W2002427601 @default.
• W3022146783 cites W2012742472 @default.
• W3022146783 cites W2014852133 @default.
• W3022146783 cites W2052533453 @default.
• W3022146783 cites W2066327668 @default.
• W3022146783 cites W2074643422 @default.
• W3022146783 cites W2109255472 @default.
• W3022146783 cites W2125085157 @default.
• W3022146783 cites W2126628495 @default.
• W3022146783 cites W2258105403 @default.
• W3022146783 cites W2295107390 @default.
• W3022146783 cites W2317354861 @default.
• W3022146783 cites W2472350142 @default.
• W3022146783 cites W2559348937 @default.
• W3022146783 cites W2590977693 @default.
• W3022146783 cites W2598545345 @default.
• W3022146783 cites W2614221804 @default.
• W3022146783 cites W2788159735 @default.
• W3022146783 cites W2792806930 @default.
• W3022146783 cites W2897550403 @default.
• W3022146783 cites W2947304242 @default.
• W3022146783 cites W2962951509 @default.
• W3022146783 cites W2979395867 @default.
• W3022146783 cites W2996133292 @default.
• W3022146783 cites W2997393112 @default.
• W3022146783 cites W3100800971 @default.
• W3022146783 cites W401751405 @default.
• W3022146783 cites W4206192903 @default.
• W3022146783 cites W4229986818 @default.
• W3022146783 doi "https://doi.org/10.3390/s20092684" @default.
• W3022146783 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7248915" @default.
• W3022146783 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32397197" @default.
• W3022146783 hasPublicationYear "2020" @default.
• W3022146783 type Work @default.
• W3022146783 sameAs 3022146783 @default.
• W3022146783 citedByCount "16" @default.
• W3022146783 countsByYear W30221467832020 @default.
• W3022146783 countsByYear W30221467832021 @default.
• W3022146783 countsByYear W30221467832022 @default.
• W3022146783 countsByYear W30221467832023 @default.
• W3022146783 crossrefType "journal-article" @default.
• W3022146783 hasAuthorship W3022146783A5012354366 @default.
• W3022146783 hasAuthorship W3022146783A5016430669 @default.
• W3022146783 hasAuthorship W3022146783A5030022647 @default.
• W3022146783 hasAuthorship W3022146783A5041192515 @default.
• W3022146783 hasAuthorship W3022146783A5044010094 @default.
• W3022146783 hasBestOaLocation W30221467831 @default.
• W3022146783 hasConcept C108583219 @default.
• W3022146783 hasConcept C119857082 @default.
• W3022146783 hasConcept C134306372 @default.
• W3022146783 hasConcept C136389625 @default.
• W3022146783 hasConcept C139676723 @default.
• W3022146783 hasConcept C154945302 @default.
• W3022146783 hasConcept C165696696 @default.
• W3022146783 hasConcept C2983860417 @default.
• W3022146783 hasConcept C33923547 @default.
• W3022146783 hasConcept C38652104 @default.
• W3022146783 hasConcept C41008148 @default.
• W3022146783 hasConcept C50644808 @default.
• W3022146783 hasConcept C58973888 @default.
• W3022146783 hasConcept C6528762 @default.
• W3022146783 hasConcept C95623464 @default.
• W3022146783 hasConceptScore W3022146783C108583219 @default.
• W3022146783 hasConceptScore W3022146783C119857082 @default.
• W3022146783 hasConceptScore W3022146783C134306372 @default.
• W3022146783 hasConceptScore W3022146783C136389625 @default.
• W3022146783 hasConceptScore W3022146783C139676723 @default.
• W3022146783 hasConceptScore W3022146783C154945302 @default.
• W3022146783 hasConceptScore W3022146783C165696696 @default.
• W3022146783 hasConceptScore W3022146783C2983860417 @default.
• W3022146783 hasConceptScore W3022146783C33923547 @default.
• W3022146783 hasConceptScore W3022146783C38652104 @default.
• W3022146783 hasConceptScore W3022146783C41008148 @default.
• W3022146783 hasConceptScore W3022146783C50644808 @default.
• W3022146783 hasConceptScore W3022146783C58973888 @default.
• W3022146783 hasConceptScore W3022146783C6528762 @default.
• W3022146783 hasConceptScore W3022146783C95623464 @default.
• W3022146783 hasIssue "9" @default.
• W3022146783 hasLocation W30221467831 @default.
• W3022146783 hasLocation W30221467832 @default.
• W3022146783 hasLocation W30221467833 @default.
• W3022146783 hasLocation W30221467834 @default.
• W3022146783 hasLocation W30221467835 @default.
• W3022146783 hasOpenAccess W3022146783 @default.
• W3022146783 hasPrimaryLocation W30221467831 @default.
• W3022146783 hasRelatedWork W2908875379 @default.
• W3022146783 hasRelatedWork W2947809439 @default.

• next