Dynamic Adaptation on Non-Stationary Visual Domains

Abstract

Domain adaptation aims to learn models on a supervised source domain that perform well on an unsupervised target. Prior work has examined domain adaptation in the context of stationary domain shifts, i.e. static data sets. However, with large-scale or dynamic data sources, data from a defined domain is not usually available all at once. For instance, in a streaming data scenario, dataset statistics effectively become a function of time. We introduce a framework for adaptation over non-stationary distribution shifts applicable to large-scale and streaming data scenarios. The model is adapted sequentially over incoming unsupervised streaming data batches. This enables improvements over several batches without the need for any additionally annotated data. To demonstrate the effectiveness of our proposed framework, we modify associative domain adaptation to work well on source and target data batches with unequal class distributions. We apply our method to several adaptation benchmark datasets for classification and show improved classifier accuracy not only for the currently adapted batch, but also when applied on future stream batches. Furthermore, we show the applicability of our associative learning modifications to semantic segmentation, where we achieve competitive results.

References in corpus (14)

• Learning Transferable Features with Deep Adaptation Networks
• Deep Visual Domain Adaptation: A Survey
• Unsupervised Domain Adaptation with Residual Transfer Networks
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
• Adversarial Discriminative Domain Adaptation
• Deep CORAL: Correlation Alignment for Deep Domain Adaptation
• Domain Adaptation for Visual Applications: A Comprehensive Survey
• Playing for Data: Ground Truth from Computer Games
• Deep Transfer Learning with Joint Adaptation Networks
• Learning by Association - A versatile semi-supervised training method for neural networks
• Associative Domain Adaptation
• Active Transfer Learning with Zero-Shot Priors: Reusing Past Datasets for Future Tasks
• A Fully Convolutional Tri-branch Network (FCTN) for Domain Adaptation