Learning Signer-Invariant Representations with Adversarial Training

• Type: Article in International Conference Proceedings Book
• Date: 2020

Authors

Pedro M. Ferreira (Author) Other; Diogo Pernes (Author) FEUP; Ana Rebelo (Author) Other; Jaime S. Cardoso (Author) FEUP

Conference proceedings International

Title: TWELFTH INTERNATIONAL CONFERENCE ON MACHINE VISION (ICMV 2019)

12th International Conference on Machine Vision (ICMV)

Amsterdam, NETHERLANDS, NOV 16-18, 2019

Indexing

ISI Web of Knowledge - 0 Citations

Scopus - 0 Citations

INSPEC

Other information

Authenticus ID: P-00R-P8G

DOI: 10.1117/12.2559534

Abstract (EN): Sign Language Recognition (SLR) has become an appealing topic in modern societies because such technology can ideally be used to bridge the gap between deaf and hearing people. Although important steps have been made towards the development of real-world SLR systems, signer-independent SLR is still one of the bottleneck problems of this research field. In this regard, we propose a deep neural network along with an adversarial training objective, specifically designed to address the signer-independent problem. Concretely speaking, the proposed model consists of an encoder, mapping from input images to latent representations, and two classifiers operating on these underlying representations: (i) the signclassifier, for predicting the class/sign labels, and (ii) the signer-classifier, for predicting their signer identities. During the learning stage, the encoder is simultaneously trained to help the sign-classifier as much as possible while trying to fool the signer-classifier. This adversarial training procedure allows learning signer-invariant latent representations that are in fact highly discriminative for sign recognition. Experimental results demonstrate the effectiveness of the proposed model and its capability of dealing with the large inter-signer variations.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 10