Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385436268> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4385436268 abstract "Handwriting recognition has seen significant success with the use of deep learning. However, a persistent shortcoming of neural networks is that they are not well-equipped to deal with shifting data distributions. In the field of handwritten text recognition (HTR), this shows itself in poor recognition accuracy for writers that are not similar to those seen during training. An ideal HTR model should be adaptive to new writing styles in order to handle the vast amount of possible writing styles. In this paper, we explore how HTR models can be made writer adaptive by using only a handful of examples from a new writer (e.g., 16 examples) for adaptation. Two HTR architectures are used as base models, using a ResNet backbone along with either an LSTM or Transformer sequence decoder. Using these base models, two methods are considered to make them writer adaptive: 1) model-agnostic meta-learning (MAML), an algorithm commonly used for tasks such as few-shot classification, and 2) writer codes, an idea originating from automatic speech recognition. Results show that an HTR-specific version of MAML known as MetaHTR improves performance compared to the baseline with a 1.4 to 2.0 improvement in word error rate (WER). The improvement due to writer adaptation is between 0.2 and 0.7 WER, where a deeper model seems to lend itself better to adaptation using MetaHTR than a shallower model. However, applying MetaHTR to larger HTR models or sentence-level HTR may become prohibitive due to its high computational and memory requirements. Lastly, writer codes based on learned features or Hinge statistical features did not lead to improved recognition performance." @default.
- W4385436268 created "2023-08-01" @default.
- W4385436268 creator A5017566697 @default.
- W4385436268 creator A5028858025 @default.
- W4385436268 creator A5092574601 @default.
- W4385436268 date "2023-07-11" @default.
- W4385436268 modified "2023-09-25" @default.
- W4385436268 title "Writer adaptation for offline text recognition: An exploration of neural network-based methods" @default.
- W4385436268 doi "https://doi.org/10.48550/arxiv.2307.15071" @default.
- W4385436268 hasPublicationYear "2023" @default.
- W4385436268 type Work @default.
- W4385436268 citedByCount "0" @default.
- W4385436268 crossrefType "posted-content" @default.
- W4385436268 hasAuthorship W4385436268A5017566697 @default.
- W4385436268 hasAuthorship W4385436268A5028858025 @default.
- W4385436268 hasAuthorship W4385436268A5092574601 @default.
- W4385436268 hasBestOaLocation W43854362681 @default.
- W4385436268 hasConcept C119857082 @default.
- W4385436268 hasConcept C120665830 @default.
- W4385436268 hasConcept C121332964 @default.
- W4385436268 hasConcept C13622073 @default.
- W4385436268 hasConcept C137293760 @default.
- W4385436268 hasConcept C138885662 @default.
- W4385436268 hasConcept C139807058 @default.
- W4385436268 hasConcept C154945302 @default.
- W4385436268 hasConcept C165801399 @default.
- W4385436268 hasConcept C202444582 @default.
- W4385436268 hasConcept C204321447 @default.
- W4385436268 hasConcept C2777530160 @default.
- W4385436268 hasConcept C28490314 @default.
- W4385436268 hasConcept C33923547 @default.
- W4385436268 hasConcept C40969351 @default.
- W4385436268 hasConcept C41008148 @default.
- W4385436268 hasConcept C41895202 @default.
- W4385436268 hasConcept C50644808 @default.
- W4385436268 hasConcept C62520636 @default.
- W4385436268 hasConcept C66322947 @default.
- W4385436268 hasConcept C9652623 @default.
- W4385436268 hasConceptScore W4385436268C119857082 @default.
- W4385436268 hasConceptScore W4385436268C120665830 @default.
- W4385436268 hasConceptScore W4385436268C121332964 @default.
- W4385436268 hasConceptScore W4385436268C13622073 @default.
- W4385436268 hasConceptScore W4385436268C137293760 @default.
- W4385436268 hasConceptScore W4385436268C138885662 @default.
- W4385436268 hasConceptScore W4385436268C139807058 @default.
- W4385436268 hasConceptScore W4385436268C154945302 @default.
- W4385436268 hasConceptScore W4385436268C165801399 @default.
- W4385436268 hasConceptScore W4385436268C202444582 @default.
- W4385436268 hasConceptScore W4385436268C204321447 @default.
- W4385436268 hasConceptScore W4385436268C2777530160 @default.
- W4385436268 hasConceptScore W4385436268C28490314 @default.
- W4385436268 hasConceptScore W4385436268C33923547 @default.
- W4385436268 hasConceptScore W4385436268C40969351 @default.
- W4385436268 hasConceptScore W4385436268C41008148 @default.
- W4385436268 hasConceptScore W4385436268C41895202 @default.
- W4385436268 hasConceptScore W4385436268C50644808 @default.
- W4385436268 hasConceptScore W4385436268C62520636 @default.
- W4385436268 hasConceptScore W4385436268C66322947 @default.
- W4385436268 hasConceptScore W4385436268C9652623 @default.
- W4385436268 hasLocation W43854362681 @default.
- W4385436268 hasOpenAccess W4385436268 @default.
- W4385436268 hasPrimaryLocation W43854362681 @default.
- W4385436268 hasRelatedWork W1546181631 @default.
- W4385436268 hasRelatedWork W159132833 @default.
- W4385436268 hasRelatedWork W1989705153 @default.
- W4385436268 hasRelatedWork W2047094413 @default.
- W4385436268 hasRelatedWork W2080458333 @default.
- W4385436268 hasRelatedWork W20999564 @default.
- W4385436268 hasRelatedWork W3080136773 @default.
- W4385436268 hasRelatedWork W3196747313 @default.
- W4385436268 hasRelatedWork W4308734192 @default.
- W4385436268 hasRelatedWork W4318978824 @default.
- W4385436268 isParatext "false" @default.
- W4385436268 isRetracted "false" @default.
- W4385436268 workType "article" @default.