%0 Conference Proceedings
%T Opt-SSL: An Enhanced Self-Supervised Framework for Food Recognition
%A Nil Ballus
%A Bhalaji Nagarajan
%A Petia Radeva
%B 10th Iberian Conference on Pattern Recognition and Image Analysis
%D 2022
%V 13256
%F Nil Ballus2022
%O MILAB; no menciona
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3782), last updated on Thu, 27 Apr 2023 14:53:29 +0200
%X Self-supervised Learning has been showing upbeat performance in several computer vision tasks. The popular contrastive methods make use of a Siamese architecture with different loss functions. In this work, we go deeper into two very recent state of the art frameworks, namely, SimSiam and Barlow Twins. Inspired by them, we propose a new self-supervised learning method we call Opt-SSL that combines both image and feature contrasting. We validate the proposed method on the food recognition task, showing that our proposed framework enables the self-learning networks to learn better visual representations.
%K Self-supervised
%K Contrastive learning
%K Food recognition
%U https://link.springer.com/chapter/10.1007/978-3-031-04881-4_52
%U http://dx.doi.org/10.1007/978-3-031-04881-4_52