Towards Writing Style Adaptation in Handwriting Recognition
- URL: http://arxiv.org/abs/2302.06318v1
- Date: Mon, 13 Feb 2023 12:36:17 GMT
- Title: Towards Writing Style Adaptation in Handwriting Recognition
- Authors: Jan Koh\'ut, Michal Hradi\v{s}, Martin Ki\v{s}\v{s}
- Abstract summary: We explore models with writer-dependent parameters which take the writer's identity as an additional input.
We propose a Writer Style Block (WSB), an adaptive instance normalization layer conditioned on learned embeddings of the partitions.
We show that our approach outperforms a baseline with no WSB in a writer-dependent scenario and that it is possible to estimate embeddings for new writers.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: One of the challenges of handwriting recognition is to transcribe a large
number of vastly different writing styles. State-of-the-art approaches do not
explicitly use information about the writer's style, which may be limiting
overall accuracy due to various ambiguities. We explore models with
writer-dependent parameters which take the writer's identity as an additional
input. The proposed models can be trained on datasets with partitions likely
written by a single author (e.g. single letter, diary, or chronicle). We
propose a Writer Style Block (WSB), an adaptive instance normalization layer
conditioned on learned embeddings of the partitions. We experimented with
various placements and settings of WSB and contrastively pre-trained
embeddings. We show that our approach outperforms a baseline with no WSB in a
writer-dependent scenario and that it is possible to estimate embeddings for
new writers. However, domain adaptation using simple finetuning in a
writer-independent setting provides superior accuracy at a similar
computational cost. The proposed approach should be further investigated in
terms of training stability and embedding regularization to overcome such a
baseline.
Related papers
- Capturing Style in Author and Document Representation [4.323709559692927]
We propose a new architecture that learns embeddings for both authors and documents with a stylistic constraint.
We evaluate our method on three datasets: a literary corpus extracted from the Gutenberg Project, the Blog Authorship and IMDb62.
arXiv Detail & Related papers (2024-07-18T10:01:09Z) - Fine-grained Controllable Text Generation through In-context Learning with Feedback [57.396980277089135]
We present a method for rewriting an input sentence to match specific values of nontrivial linguistic features, such as dependency depth.
In contrast to earlier work, our method uses in-context learning rather than finetuning, making it applicable in use cases where data is sparse.
arXiv Detail & Related papers (2024-06-17T08:55:48Z) - MetricPrompt: Prompting Model as a Relevance Metric for Few-shot Text
Classification [65.51149771074944]
MetricPrompt eases verbalizer design difficulty by reformulating few-shot text classification task into text pair relevance estimation task.
We conduct experiments on three widely used text classification datasets across four few-shot settings.
Results show that MetricPrompt outperforms manual verbalizer and other automatic verbalizer design methods across all few-shot settings.
arXiv Detail & Related papers (2023-06-15T06:51:35Z) - PART: Pre-trained Authorship Representation Transformer [64.78260098263489]
Authors writing documents imprint identifying information within their texts: vocabulary, registry, punctuation, misspellings, or even emoji usage.
Previous works use hand-crafted features or classification tasks to train their authorship models, leading to poor performance on out-of-domain authors.
We propose a contrastively trained model fit to learn textbfauthorship embeddings instead of semantics.
arXiv Detail & Related papers (2022-09-30T11:08:39Z) - Letter-level Online Writer Identification [86.13203975836556]
We focus on a novel problem, letter-level online writer-id, which requires only a few trajectories of written letters as identification cues.
A main challenge is that a person often writes a letter in different styles from time to time.
We refer to this problem as the variance of online writing styles (Var-O-Styles)
arXiv Detail & Related papers (2021-12-06T07:21:53Z) - Revisiting Self-Training for Few-Shot Learning of Language Model [61.173976954360334]
Unlabeled data carry rich task-relevant information, they are proven useful for few-shot learning of language model.
In this work, we revisit the self-training technique for language model fine-tuning and present a state-of-the-art prompt-based few-shot learner, SFLM.
arXiv Detail & Related papers (2021-10-04T08:51:36Z) - MetaHTR: Towards Writer-Adaptive Handwritten Text Recognition [36.12001394921506]
We propose a new approach to handwritten text recognition.
We use a novel meta-learning framework which exploits additional new-writer data.
Our framework can be easily implemented on the top of most state-of-the-art HTR models.
arXiv Detail & Related papers (2021-04-05T12:35:39Z) - Generating Handwriting via Decoupled Style Descriptors [28.31500214381889]
We introduce the Decoupled Style Descriptor model for handwriting.
It factors both character- and writer-level styles and allows our model to represent an overall greater space of styles.
In experiments, our generated results were preferred over a state of the art baseline method 88% of the time.
arXiv Detail & Related papers (2020-08-26T02:52:48Z) - Learning to Select Bi-Aspect Information for Document-Scale Text Content
Manipulation [50.01708049531156]
We focus on a new practical task, document-scale text content manipulation, which is the opposite of text style transfer.
In detail, the input is a set of structured records and a reference text for describing another recordset.
The output is a summary that accurately describes the partial content in the source recordset with the same writing style of the reference.
arXiv Detail & Related papers (2020-02-24T12:52:10Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.