Skip to Main content Skip to Navigation
Conference papers

Semi-supervised learning through adversary networks for baseline detection

Romain Karpinski 1 Abdel Belaïd 1
1 READ - Recognition of writing and analysis of documents
LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : The aim of this paper is to propose a new strategy adapted to the semantic segmentation of document images in order to extract baselines. Inspired by the work of Grüning [7], we used a convolutional model with residual layers enriched by an attention mechanism, called ARU-Net, a post-processing for the agglomeration of predictions and a data augmentation to enrich the database. Then, to consolidate the ARU-Net and help explicitly model dependencies between feature maps, we added a module of "Squeeze and Excitation" as proposed by Hu et al. [9]. Finally, to exploit the amount of unrated data available, we used a semi-supervised learning, based on ARU-Net, through the use of adversary networks. This approach has shown some interesting predictive qualities, compared to Grüning's work, with easier processing and less task-specific error correction. The resulting performance improvement is a success.
Document type :
Conference papers
Complete list of metadata

Cited literature [12 references]  Display  Hide  Download

https://hal.inria.fr/hal-02460901
Contributor : Abdel Belaid <>
Submitted on : Friday, January 31, 2020 - 1:02:54 PM
Last modification on : Friday, January 15, 2021 - 5:42:02 PM
Long-term archiving on: : Friday, May 1, 2020 - 12:51:30 PM

Identifiers

  • HAL Id : hal-02460901, version 1

Collections

Citation

Romain Karpinski, Abdel Belaïd. Semi-supervised learning through adversary networks for baseline detection. ICDAR-WML, Sep 2019, Sydney, Australia. ⟨hal-02460901⟩

Share

Metrics

Record views

92

Files downloads

335