Optical flow estimation has made great progress, but usually suffers from degradation under adverse weather. Although semi/full-supervised methods have good attempts, the domain shift between synthetic and real weather images would deteriorate their performance. To alleviate this issue, our start point is to unsupervisedly transfer knowledge source clean target degraded domain. Our key insight ...

AbstractAccurate segmentation of retinal fluids in 3D Optical Coherence Tomography images is key for diagnosis and personalized treatment eye diseases. While deep learning has been successful at this task, trained supervised models often fail that do not resemble labeled examples, e.g. acquired using different devices. We hereby propose a novel semi-supervised framework volumetric from new unla...

Traditional unsupervised domain adaptation (UDA) usually assumes that the source has labels and target no labels. In a real environment, labelled data comes from multiple different distributions. To handle this problem, multi-source (MUDA) is proposed. Multi-source aims to adapt model trained on multi-labelled domains unlabelled domain. paper, novel MUDA method by domain-specific feature recali...

In this paper an unsupervised approach to domain adaptation is presented, which exploits external knowledge sources in order to port a classification model into a new thematic domain. Our approach extracts a new feature set from documents of the target domain, and tries to align the new features to the original ones, by exploiting text relatedness from external knowledge sources, such as WordNe...

In this paper we explore the applicability of existing coreference resolution systems to a biomedical genre: radiology reports. Analysis revealed that, due to the idiosyncrasies of the domain, both the formulation of the problem of coreference resolution and its solution need significant domain adaptation work. We reformulated the task and developed an unsupervised algorithm based on heuristics...

Domain adaptation is a time consuming and costly procedure calling for the development of algorithms and tools to facilitate its automation. This paper presents an unsupervised algorithm able to learn the main concepts in event summaries. The method takes as input a set of domain summaries annotated with shallow linguistic information and produces a domain template. We demonstrate the viability...

Input-level domain adaptation reduces the burden of a neural encoder without supervision by reducing gap at input level. is widely employed in 2D visual domain, e.g., images and videos, but not utilized for 3D point clouds. We propose use input-level clouds, namely, point-level adaptation. Specifically, we to learn transformation clouds searching best combination operations on that trans...

It has been known for a while that the problem of multi-source domain adaptation can be regarded as single source task where corresponds to mixture original domains. Nonetheless, how adjust distribution weights remains an open question. Moreover, most existing work on this topic focuses only minimizing error domains and achieving domain-invariant representations, which is insufficient ensure lo...