S
Sharon Fogel
Researcher at Amazon.com
Publications - 4
Citations - 98
Sharon Fogel is an academic researcher from Amazon.com. The author has contributed to research in topics: Deep learning & Generative model. The author has an hindex of 2, co-authored 4 publications receiving 32 citations.
Papers
More filters
Proceedings ArticleDOI
ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation
TL;DR: This work presents ScrabbleGAN, a semi-supervised approach to synthesize handwritten text images that are versatile both in style and lexicon, and relies on a novel generative model which can generate images of words with an arbitrary length.
Posted Content
ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation
TL;DR: ScrabbleGAN as discussed by the authors is a semi-supervised approach to synthesize handwritten text images that are versatile both in style and lexicon using a generative model which can generate images of words with an arbitrary length.
Posted Content
TextAdaIN: Paying Attention to Shortcut Learning in Text Recognizers.
TL;DR: TextAdaIN as mentioned in this paper proposes to view each feature map as a sequence of elements and deliberately mismatching fine-grained feature statistics between elements in a mini-batch to prevent the network from overfitting to local statistics.
Posted Content
TextAdaIN: Fine-Grained AdaIN for Robust Text Recognition.
TL;DR: TextAdaIN as mentioned in this paper uses local distortions in the feature map which prevent the network from overfitting to the local statistics. But it does so by deliberately mismatching fine-grained feature statistics between samples in a mini-batch.