Self-supervised Domain Adaptation for Computer Vision Tasks
Recent progress of self-supervised visual representation learning has achieved remarkable success on many challenging computer vision benchmarks. However, whether these techniques can be used for domain adaptation has not been explored. In this work, we propose a generic method for self-supervised domain adaptation, using object recognition and semantic segmentation of urban scenes as use cases. Focusing on simple pretext/auxiliary tasks (e.g. image rotation prediction), we assess different learning strategies to improve domain adaptation effectiveness by self-supervision. Additionally, we propose two complementary strategies to further boost the domain adaptation accuracy on semantic segmentation within our method, consisting of prediction layer alignment and batch normalization calibration. The experimental results show adaptation levels comparable to most studied domain adaptation methods, thus, bringing self-supervision as a new alternative for reaching domain adaptation. The code is available at https://github.com/Jiaolong/self-supervised-da.
Code (1)
Tasks
Domain AdaptationObject RecognitionRepresentation LearningSegmentationSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
VESSA: Video-based objEct-centric Self-Supervised Adaptation for Visual Foundation Models
Foundation models have advanced computer vision by enabling strong performance across diverse tasks through large-scale pretraining and supervised fine-tuning. However, they may underperform in domains with distribution …
Self-Supervised LearningLearning to Adapt Multi-View Stereo by Self-Supervision
3D scene reconstruction from multiple views is an important classical problem in computer vision. Deep learning based approaches have recently demonstrated impressive reconstruction results. When training such models, se…
3D Scene ReconstructionMeta-LearningDon't Worry About the Weather: Unsupervised Condition-Dependent Domain Adaptation
Modern models that perform system-critical tasks such as segmentation and localization exhibit good performance and robustness under ideal conditions (i.e. daytime, overcast) but performance degrades quickly and often ca…
Domain AdaptationSegmentationSemantic SegmentationSelf-supervised Domain Adaptation in Crowd Counting
Self-training crowd counting has not been attentively explored though it is one of the important challenges in computer vision. In practice, the fully supervised methods usually require an intensive resource of manual an…
Crowd CountingDomain AdaptationMSDA: Combining Pseudo-labeling and Self-Supervision for Unsupervised Domain Adaptation in ASR
In this work, we investigate the Meta PL unsupervised domain adaptation framework for Automatic Speech Recognition (ASR). We introduce a Multi-Stage Domain Adaptation pipeline (MSDA), a sample-efficient, two-stage adapta…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Domain AdaptationSelf-Supervised Learning+3