Open compound domain adaptation (OCDA) has emerged as a practical adaptation setting which considers a single labeled source domain against a compound of multi-modal unlabeled target data in order to generalize better on novel unseen domains. We hypothesize that an improved disentanglement of domain-related and task-related factors of dense intermediate layer features can greatly aid OCDA. Prior-arts attempt this indirectly by employing adversarial domain discriminators on the spatial CNN output. However, we find that latent features derived from the Fourier-based amplitude spectrum of deep CNN features hold a more tractable mapping with domain discrimination. Motivated by this, we propose a novel feature space Amplitude Spectrum Transformation (AST). During adaptation, we employ the AST auto-encoder for two purposes. First, carefully mined source-target instance pairs undergo a simulation of cross-domain feature stylization (AST-Sim) at a particular layer by altering the AST-latent. Second, AST operating at a later layer is tasked to normalize (AST-Norm) the domain content by fixing its latent to a mean prototype. Our simplified adaptation technique is not only clustering-free but also free from complex adversarial alignment. We achieve leading performance against the prior arts on the OCDA scene segmentation benchmarks.
翻译:开放的复合域适应(OCDA)是一个实际的适应环境,它考虑到一个单一的标签源域,与多式无标签的目标数据组合相对,以更好地普及新的无形域。我们假设,在密集的中间层特征中,改进与域相关和任务相关因素的分解,可以极大地帮助OCDA。先前的尝试是通过在CNN空间输出上使用对抗性域区分器间接地尝试的。然而,我们发现,由基于Fourier的远端CNN特征振动频谱产生的潜伏特征,具有更易移动的域差异绘图。受此驱动,我们提出一个新颖的地貌空间振动光谱变形(ASTST)。在适应期间,我们使用AST自动变相器用于两个目的。首先,仔细挖掘的源目标对子对一个特定的层进行模拟,改变AST-Sim。在后一个层运行的AST具有比A-Norm),其域域内内容通过固定其潜面的面面面面面面图比前的原型,我们简化的调整技术也只能从对面的面的面上进行自我调整。