Corpus ID: 219559306

Self-Supervised Relational Reasoning for Representation Learning

@article{Patacchiola2020SelfSupervisedRR,
  title={Self-Supervised Relational Reasoning for Representation Learning},
  author={Massimiliano Patacchiola and Amos J. Storkey},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.05849}
}
  • Massimiliano Patacchiola, Amos J. Storkey
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • In self-supervised learning, a system is tasked with achieving a surrogate objective by defining alternative targets on a set of unlabeled data. The aim is to build useful representations that can be used in downstream tasks, without costly manual annotation. In this work, we propose a novel self-supervised formulation of relational reasoning that allows a learner to bootstrap a signal from information implicit in unlabeled data. Training a relation head to discriminate how entities relate to… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 35 REFERENCES

    ImageNet Large Scale Visual Recognition Challenge

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Context Encoders: Feature Learning by Inpainting

    VIEW 1 EXCERPT