MoDA: Map style transfer for self-supervised Domain Adaptation of embodied agents
We propose a domain adaptation method, MoDA, which adapts a pretrained embodied agent to a new, noisy environment without ground-truth supervision. Map-based memory provides important contextual information for visual navigation, and exhibits unique spatial structure mainly composed of flat walls and rectangular obstacles. Our adaptation approach encourages the inherent regularities on the estimated maps to guide the agent to overcome the prevalent domain discrepancy in a novel environment. Specifically, we propose an efficient learning curriculum to handle the visual and dynamics corruptions in an online manner, self-supervised with pseudo clean maps generated by style transfer networks. Because the map-based representation provides spatial knowledge for the agent's policy, our formulation can deploy the pretrained policy networks from simulators in a new setting. We evaluate MoDA in various practical scenarios and show that our proposed method quickly enhances the agent's performance in downstream tasks including localization, mapping, exploration, and point-goal navigation.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationStyle TransferVisual NavigationSimilar Papers 제목 키워드 기반
Random Style Transfer based Domain Generalization Networks Integrating Shape and Spatial Information
Deep learning (DL)-based models have demonstrated good performance in medical image segmentation. However, the models trained on a known dataset often fail when performed on an unseen dataset collected from different cen…
Domain GeneralizationImage SegmentationMedical Image SegmentationSegmentation+3ALADIN-NST: Self-supervised disentangled representation learning of artistic style through Neural Style Transfer
Representation learning aims to discover individual salient features of a domain in a compact and descriptive form that strongly identifies the unique characteristics of a given sample respective to its domain. Existing …
DescriptiveDisentanglementRepresentation LearningStyle TransferSHMT: Self-supervised Hierarchical Makeup Transfer via Latent Diffusion Models
This paper studies the challenging task of makeup transfer, which aims to apply diverse makeup styles precisely and naturally to a given facial image. Due to the absence of paired data, current methods typically synthesi…
SILT: Self-supervised Lighting Transfer Using Implicit Image Decomposition
We present SILT, a Self-supervised Implicit Lighting Transfer method. Unlike previous research on scene relighting, we do not seek to apply arbitrary new lighting configurations to a given scene. Instead, we wish to tran…
Self-Supervised VQ-VAE for One-Shot Music Style Transfer
Neural style transfer, allowing to apply the artistic style of one image to another, has become one of the most widely showcased computer vision applications shortly after its introduction. In contrast, related tasks in …
Music Style TransferSelf-Supervised LearningStyle Transfer