Leveraging Unannotated Sign Language Data via a Robust Data Augmentation Method for Contrastive Representation Learning

Ariel Basso Madjoukeng, Pierre Poitier, Belise Edith Kenmogne, Adelaide Couplet, Margaux Leleu, Frenay Benoit


Abstract
Contrastive learning is a deep learning paradigm that allows the learning of useful representations without annotations. In many fields, including sign language recognition (SLR), contrastive approaches have proven to be very effective for developing pretrained models. To learn representations, they generate augmented variants of an instance through augmentation techniques and then maximize their similarities. The quality of the learned representations is strongly correlated with the augmentations used during training. In several fields, specialized augmentations have been developed and adopted. However, in SLR, we observed two trends: contrastive-based SLR approaches often rely on augmentations that are not realistic for the application (e.g., vertical flip, excessive rotations); specialized augmentation methods lack robustness. Hence, when they are used as a starting point for contrastive algorithms, the learned representations are often irrelevant, and sometimes sensitive. These issues considerably affect the accuracy of SLR models on downstream tasks. In response, this paper proposes a robust augmentation method specially designed for contrastive approaches applied to SLR. The results show an improvement in accuracy during linear evaluation and semi-supervised learning with only 30% of annotations.
Anthology ID:
2026.signlang-1.2
Volume:
Proceedings of the LREC 2026 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Eleni Efthimiou, Stavroula-Evita Fotinea, Thomas Hanke, Julie A. Hochgesang, Johanna Mesch, Marc Schulder
Venues:
SignLang | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
10–16
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-signlang-02
DOI:
10.63317/4qnrmhtbv9cz
Bibkey:
Cite (ACL):
Ariel Basso Madjoukeng, Pierre Poitier, Belise Edith Kenmogne, Adelaide Couplet, Margaux Leleu, and Frenay Benoit. 2026. Leveraging Unannotated Sign Language Data via a Robust Data Augmentation Method for Contrastive Representation Learning. In Proceedings of the LREC 2026 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion, pages 10–16, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
Leveraging Unannotated Sign Language Data via a Robust Data Augmentation Method for Contrastive Representation Learning (Basso Madjoukeng et al., SignLang 2026)
Copy Citation: