no code implementations • 19 Sep 2023 • Sorachi Kurita, Satoshi Oyama, Itsuki Noda
In scene graph generation (SGG), learning with cross-entropy loss yields biased predictions owing to the severe imbalance in the distribution of the relationship labels in the dataset.
no code implementations • 22 Oct 2022 • Hisashi Kashima, Satoshi Oyama, Hiromi Arai, Junichiro Mori
Human computation is an approach to solving problems that prove difficult using AI only, and involves the cooperation of many humans.
1 code implementation • 19 Oct 2020 • Kyohei Atarashi, Satoshi Oyama, Masahito Kurihara
For feature interaction selection, our proposed regularizer makes the feature interaction matrix sparse without a restriction on sparsity patterns imposed by the existing methods.