arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.09949cs.CV
收藏

生成器模型的稀疏潜在表示学习

Learning Sparse Latent Representations for Generator Model

Stevens Institute of Technology(史蒂文斯理工学院)

Hanao Li, Tian Han

摘要:

稀疏性是一个理想的属性。与密集模型相比,它可以导致更高效和更有效的表示。同时,由于其复杂性,稀疏潜在表示的学习一直是计算机视觉和机器学习领域的一个具有挑战性的问题。在本文中,我们提出了一种新的无监督学习方法,以加强稀疏的潜在空间的发电机模型与逐渐稀疏的尖峰和板坯分布作为我们的先验。我们的模型仅由一个自上而下的生成器网络组成,该网络将潜在变量映射到观测数据。潜变量可以使用基于非持续梯度的方法沿着生成器后验方向推断。推理步骤中的Spike和Slab正则化可以将无信息的潜在维度推向零以诱导稀疏性。大量的实验表明,该模型可以保留大部分的信息,从原始图像的稀疏表示,同时证明了改善的结果相比,其他现有的方法。我们观察到,我们的模型可以学习解开的语义,并增加潜在代码的可解释性,同时提高分类和去噪任务的鲁棒性。

英文摘要:

Sparsity is a desirable attribute. It can lead to more efficient and more effective representations compared to the dense model. Meanwhile, learning sparse latent representations has been a challenging problem in the field of computer vision and machine learning due to its complexity. In this paper, we present a new unsupervised learning method to enforce sparsity on the latent space for the generator model with a gradually sparsified spike and slab distribution as our prior. Our model consists of only one top-down generator network that maps the latent variable to the observed data. Latent variables can be inferred following generator posterior direction using non-persistent gradient based method. Spike and Slab regularization in the inference step can push non-informative latent dimensions towards zero to induce sparsity. Extensive experiments show the model can preserve majority of the information from original images with sparse representations while demonstrating improved results compared to other existing methods. We observe that our model can learn disentangled semantics and increase explainability of the latent codes while boosting the robustness in the task of classification and denoising.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑