TY  - CONF
AU  - Nil Ballus
AU  - Bhalaji Nagarajan
AU  - Petia Radeva
A2  - IbPRIA
PY  - 2022//
TI  - Opt-SSL: An Enhanced Self-Supervised Framework for Food Recognition
T2  - LNCS
BT  - 10th Iberian Conference on Pattern Recognition and Image Analysis
VL  - 13256
KW  - Self-supervised
KW  - Contrastive learning
KW  - Food recognition
N2  - 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.
UR  - https://link.springer.com/chapter/10.1007/978-3-031-04881-4_52
UR  - http://dx.doi.org/10.1007/978-3-031-04881-4_52
N1  - MILAB; no menciona
ID  - Nil Ballus2022
ER  -