融合条件子模块GAN与程序化弱监督
Fusing Conditional Submodular GAN and Programmatic Weak Supervision
AI总结：
针对WSGAN融合PWS与生成模型时存在的潜在因子非类别特异、标签噪声影响生成质量的问题，提出噪声感知分类器与子模块子集选择方法，在多数据集上实现优于现有SOTA的效果。
摘要：
程序化弱监督（Programmatic Weak Supervision, PWS）与生成模型是帮助研究人员最大化现有数据集效用、无需进行繁重数据收集和人工标注流程的关键工具。PWS利用多种弱监督技术估计数据的潜在类别标签，而生成模型主要聚焦于从给定数据集的潜在分布中采样。尽管这两类方法具备互补潜力，但此前大多被独立研究。近期，WSGAN提出了一种融合这两种模型的机制：该方法利用InfoGAN的离散潜在因子训练标签模型，并借助标签模型的类别相关信息生成特定类别的图像。然而，InfoGAN学习到的解耦潜在因子未必具有类别特异性，可能会影响标签模型的准确性。此外，标签模型的预测本质上通常存在噪声，会对GAN生成的图像质量产生不利影响。在本研究中，我们通过两种方式应对这些挑战：（1）利用标签模型生成的伪标签实现一个噪声感知分类器；（2）利用噪声感知分类器的预测训练标签模型并生成类别条件图像。此外，我们还研究了在伪标签的确定不确定性预算内，使用数据集子集训练分类器的效果。我们通过将子集选择问题形式化为一个带伪标签熵背包约束的子模块最大化目标来实现这一点。我们在多个数据集上开展了实验，证明了我们的方法在多项任务上相较于当前最优方法的有效性。
英文摘要：
Programmatic Weak Supervision (PWS) and generative models serve as crucial tools that enable researchers to maximize the utility of existing datasets without resorting to laborious data gathering and manual annotation processes. PWS uses various weak supervision techniques to estimate the underlying class labels of data, while generative models primarily concentrate on sampling from the underlying distribution of the given dataset. Although these methods have the potential to complement each other, they have mostly been studied independently. Recently, WSGAN proposed a mechanism to fuse these two models. Their approach utilizes the discrete latent factors of InfoGAN to train the label model and leverages the class-dependent information of the label model to generate images of specific classes. However, the disentangled latent factors learned by InfoGAN might not necessarily be class-specific and could potentially affect the label model's accuracy. Moreover, prediction made by the label model is often noisy in nature and can have a detrimental impact on the quality of images generated by GAN. In our work, we address these challenges by (i) implementing a noise-aware classifier using the pseudo labels generated by the label model (ii) utilizing the noise-aware classifier's prediction to train the label model and generate class-conditional images. Additionally, we also investigate the effect of training the classifier with a subset of the dataset within a defined uncertainty budget on pseudo labels. We accomplish this by formalizing the subset selection problem as a submodular maximization objective with a knapsack constraint on the entropy of pseudo labels. We conduct experiments on multiple datasets and demonstrate the efficacy of our methods on several tasks vis-a-vis the current state-of-the-art methods.
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。
