Incremental Adversarial Domain Adaptation for Continually Changing Environments

Abstract

Continuous appearance shifts such as changes in weather and lighting conditions can impact the performance of deployed machine learning models. While unsupervised domain adaptation aims to address this challenge, current approaches do not utilise the continuity of the occurring shifts. In particular, many robotics applications exhibit these conditions and thus facilitate the potential to incrementally adapt a learnt model over minor shifts which integrate to massive differences over time. Our work presents an adversarial approach for lifelong, incremental domain adaptation which benefits from unsupervised alignment to a series of intermediate domains which successively diverge from the labelled source domain. We empirically demonstrate that our incremental approach improves handling of large appearance changes, e.g. day to night, on a traversable-path segmentation task compared with a direct, single alignment step approach. Furthermore, by approximating the feature distribution for the source domain with a generative adversarial network, the deployment module can be rendered fully independent of retaining potentially large amounts of the related source training data for only a minor reduction in performance.

Adversarial discriminative sim-to-real transfer of visuo-motor policies

“…Similar to GANs (Goodfellow et al 2014), adversarial approaches are also proposed for domain adaptation in classification contexts such as handwritten digit recognition (Tzeng et al 2017;Luo et al 2017;Ge et al 2017), place classification and segmentation (Wulfmeier et al 2017(Wulfmeier et al , 2018. Another similar approach is domain confusion, whose feasibility has been verified in object recognition (Tzeng et al 2015) and fine-grained recoginition (Gebru et al 2017).…”

“…Aiming for more data-efficient learning, an adversarial approach similar to GANs (Goodfellow et al 2014) was proposed to learn a classifier for grasping using labelled synthetic and unlabelled real data (Bousmalis et al 2018). However, most existing works used adversarial approaches for classification tasks such as incremental adversarial domain adaptation for drivable-path segmentation (Wulfmeier et al 2018). To the best of our knowledge, there is no existing work using adversarial methods for the transfer of regression tasks.…”

Don’t Worry About the Weather: Unsupervised Condition-Dependent Domain Adaptation

“…The authors of [28] present an approach to incremental online domain adaptation, making use of unsupervised training by employing domain confusion at the level of encoder features from both target and source domains, while slowly shifting both domains through a range of incremental appearance changes (e.g. day to night).…”

Multi-Step Online Unsupervised Domain Adaptation

“…Mancini et al [12] adopted a batch normalization technique [13] for online domain adaptation, which was restricted to the kitting task only. Wulfmeier et al [9] expanded his previous work on GANs 1 This work was supported in part by the National Science Foundation under Grant IIS-1813935. Any opinion, findings, and conclusions or recommendations expressed in this material are those of the authors and do not necessarily reflect the views of the National Science Foundation.…”