Negative-free contrastive learning has attracted a lot of attention with simplicity and impressive performance for large-scale pretraining. But its disentanglement property remains unexplored. In this paper, we take different negative-free contrastive learning methods to study the disentanglement property of this genre of self-supervised methods empirically. We find the existing disentanglement metrics fail to make meaningful measurements for the high-dimensional representation model so we propose a new disentanglement metric based on Mutual Information between representation and data factors. With the proposed metric, we benchmark the disentanglement property of negative-free contrastive learning for the first time, on both popular synthetic datasets and a real-world dataset CelebA. Our study shows that the investigated methods can learn a well-disentangled subset of representation. We extend the study of the disentangled representation learning to high-dimensional representation space and negative-free contrastive learning for the first time. The implementation of the proposed metric is available at \url{https://github.com/noahcao/disentanglement_lib_med}.
翻译:以简单和令人印象深刻的性能进行大规模培训前的对比性反向学习已经引起人们的极大关注。 但是,它的分解属性仍未被探索。 在本文中,我们采用了不同的反面对比性学习方法,从经验上研究这种自我监督方法模式的分解属性。我们发现现有的分解度量未能对高维代表模型进行有意义的测量,因此我们基于相互信息提出一个新的分解度量。在拟议指标中,我们首次将负面零对比性学习的分解属性以流行合成数据集和真实世界数据集为基准。我们的研究显示,所调查的方法可以了解一个非常分解的代言组合。我们第一次将关于分解性代表学习的研究推广到高维代表性空间和负自由对比性学习。拟议指标的实施可以在\url{https://github.com/noahao/dientclementmentment_lib_med}上查阅。