Deep neural networks have demonstrated their ability to automatically extract meaningful features from data. However, in supervised learning, information specific to the dataset used for training, but irrelevant to the task at hand, may remain encoded in the extracted representations. This remaining information introduces a domain-specific bias, weakening the generalization performance. In this work, we propose splitting the information into a task-related representation and its complementary context representation. We propose an original method, combining adversarial feature predictors and cyclic reconstruction, to disentangle these two representations in the single-domain supervised case. We then adapt this method to the unsupervised domain adaptation problem, consisting of training a model capable of performing on both a source and a target domain. In particular, our method promotes disentanglement in the target domain, despite the absence of training labels. This enables the isolation of task-specific information from both domains and a projection into a common representation. The task-specific representation allows efficient transfer of knowledge acquired from the source domain to the target domain. In the single-domain case, we demonstrate the quality of our representations on information retrieval tasks and the generalization benefits induced by sharpened task-specific representations. We then validate the proposed method on several classical domain adaptation benchmarks and illustrate the benefits of disentanglement for domain adaptation.
翻译:深神经网络显示它们有能力自动从数据中获取有意义的特征。然而,在有监督的学习中,用于培训的数据集所特有的、但与手头任务无关的信息,可能仍然在抽取的演示中进行编码。这一剩余信息含有特定领域的偏差,削弱了一般化绩效。在这项工作中,我们建议将信息分为与任务相关的表述及其互补背景表述。我们提出了一个原始方法,将对抗性特征预测器和周期性重建结合起来,在单一领域监督的案例中将这两种表达方式分解为一体。然后,我们调整这一方法,以适应未受监督的领域适应问题,包括培训一种能够在源和目标领域执行的模型。特别是,尽管没有培训标签,我们的方法还是促进了目标领域的脱节,这样可以将特定任务的信息从两个领域和预测分成一个共同的表述。我们提出了一种原始方法,将从源领域获取的知识有效地转移到目标领域。在单一领域案例中,我们随后展示了信息检索任务说明的质量,并展示了可同时在源和目标领域执行的模式下实施的模式,我们通过强化领域性任务调整的拟议基准,从而验证了某些领域调整的具体度。