Unsupervised Domain Adaptation with Temporal-Consistent Self-Training for 3D Hand-Object Joint Reconstruction
Deep learning-solutions for hand-object 3D pose and shape estimation are now very effective when an annotated dataset is available to train them to handle the scenarios and lighting conditions they will encounter at test time. Unfortunately, this is not always the case, and one often has to resort to training them on synthetic data, which does not guarantee that they will work well in real situations. In this paper, we introduce an effective approach to addressing this challenge by exploiting 3D geometric constraints within a cycle generative adversarial network (CycleGAN) to perform domain adaptation. Furthermore, in contrast to most existing works, which fail to leverage the rich temporal information available in unlabeled real videos as a source of supervision, we propose to enforce short- and long-term temporal consistency to fine-tune the domain-adapted model in a self-supervised fashion. We will demonstrate that our approach outperforms state-of-the-art 3D hand-object joint reconstruction methods on three widely-used benchmarks and will make our code publicly available.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationGenerative Adversarial NetworkUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation
Deep convolutional neural networks have considerably improved state-of-the-art results for semantic segmentation. Nevertheless, even modern architectures lack the ability to generalize well to a test dataset that origina…
Contrastive LearningDomain AdaptationSemantic SegmentationSynthetic-to-Real Translation+2Prompt Ensemble Self-training for Open-Vocabulary Domain Adaptation
Traditional domain adaptation assumes the same vocabulary across source and target domains, which often struggles with limited transfer flexibility and efficiency while handling target domains with different vocabularies…
Domain AdaptationUnsupervised Domain AdaptationSelf-Adaptation for Unsupervised Domain Adaptation
Lack of labelled data in the target domain for training is a common problem in domain adaptation. To overcome this problem, we propose a novel unsupervised domain adaptation method that combines projection and self-train…
Domain AdaptationUnsupervised Domain AdaptationMemory Consistent Unsupervised Off-the-Shelf Model Adaptation for Source-Relaxed Medical Image Segmentation
Unsupervised domain adaptation (UDA) has been a vital protocol for migrating information learned from a labeled source domain to facilitate the implementation in an unlabeled heterogeneous target domain. Although UDA is …
Brain Tumor SegmentationDomain AdaptationImage SegmentationMedical Image Segmentation+5Towards Self-similarity Consistency and Feature Discrimination for Unsupervised Domain Adaptation
Recent advances in unsupervised domain adaptation mainly focus on learning shared representations by global distribution alignment without considering class information across domains. The neglect of class information, h…
Domain AdaptationUnsupervised Domain Adaptation