yipala的博客

AdderNet: Do We Really Need Multiplications in Deep Learning? （加法神经网络） On Positive-Unlabeled Classification in GAN （PU+GAN） Multi-Modal Domain Adaptation for Fine-Grained Action Recognition（细粒度动作识别） ...

AETvs. AED:UnsupervisedRepresentationLearningbyAuto-Encoding TransformationsratherthanData https://arxiv.org/abs/1901.04596 基于变换的无监督训练 一个是以“预测变换”作为自监督信号进行训练的模型，代表是Rotation Net (RotNet)[1] 和AutoEncodin...

https://www.jiqizhixin.com/articles/2019-01-31-12