Search Results for author: Dar-Shyang Lee

Found 4 papers, 4 papers with code

Domain Conditional Predictors for Domain Adaptation

1 code implementation25 Jun 2021 Joao Monteiro, Xavier Gibert, Jianqiao Feng, Vincent Dumoulin, Dar-Shyang Lee

Domain adaptation approaches thus appeared as a useful framework yielding extra flexibility in that distinct train and test data distributions are supported, provided that other assumptions are satisfied such as covariate shift, which expects the conditional distributions over labels to be independent of the underlying data distribution.

Domain Adaptation

Attention-based Extraction of Structured Information from Street View Imagery

3 code implementations11 Apr 2017 Zbigniew Wojna, Alex Gorban, Dar-Shyang Lee, Kevin Murphy, Qian Yu, Yeqing Li, Julian Ibarz

We present a neural network model - based on CNNs, RNNs and a novel attention mechanism - which achieves 84. 2% accuracy on the challenging French Street Name Signs (FSNS) dataset, significantly outperforming the previous state of the art (Smith'16), which achieved 72. 46%.

Optical Character Recognition (OCR)

End-to-End Interpretation of the French Street Name Signs Dataset

4 code implementations13 Feb 2017 Raymond Smith, Chunhui Gu, Dar-Shyang Lee, Huiyi Hu, Ranjith Unnikrishnan, Julian Ibarz, Sacha Arnoud, Sophia Lin

We introduce the French Street Name Signs (FSNS) Dataset consisting of more than a million images of street name signs cropped from Google Street View images of France.

Optical Character Recognition (OCR)

Cannot find the paper you are looking for? You can Submit a new open access paper.