paper-with-me

Papers

MoDA: Map style transfer for self-supervised Domain Adaptation of embodied agents

2022-11-29 · Eun Sun Lee, Junho Kim, SangWon Park, Young Min Kim

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.

📄 PDF Abstract BibTeX arXiv:2211.15992

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationStyle TransferVisual Navigation

Similar Papers 제목 키워드 기반

Random Style Transfer based Domain Generalization Networks Integrating Shape and Spatial Information

2020-08-27 · Lei Li, Veronika A. Zimmer, Wangbin Ding, Fuping Wu 외

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+3

ALADIN-NST: Self-supervised disentangled representation learning of artistic style through Neural Style Transfer

2023-04-12 · Dan Ruta, Gemma Canet Tarres, Alexander Black, Andrew Gilbert 외

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 Transfer

SHMT: Self-supervised Hierarchical Makeup Transfer via Latent Diffusion Models

2024-12-15 · Zhaoyang Sun, Shengwu Xiong, Yaxiong Chen, Fei Du 외

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

2021-10-25 · Nikolina Kubiak, Armin Mustafa, Graeme Phillipson, Stephen Jolly 외

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

2021-02-10 · Ondřej Cífka, Alexey Ozerov, Umut Şimşekli, Gaël Richard

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