Deep learned compact binary descriptor with a lightweight network-in-network architecture for visual description

• Main Authors: Bandara, Ravimal, Ranathunga, Lochandaka, Abdullah, Nor Aniza
• Format: Article
• Published: Springer 2021
• Subjects: QA75 Electronic computers. Computer science
• Online Access: http://eprints.um.edu.my/26950/
• Institution: Universiti Malaya

Binary descriptors have been widely used for real-time image retrieval and correspondence matching. However, most of the learned descriptors are obtained using a large deep neural network (DNN) with several million parameters, and the learned binary codes are generally not invariant to many geometri...