AbstractUnsupervised Domain Adaptation (UDA) aims at reducing the domain gap between training and testing data is, in most cases, carried out offline manner. However, changes may occur continuously unpredictably during deployment (e.g. sudden weather changes). In such conditions, deep neural networks witness dramatic drops accuracy adaptation not be enough to contrast it. this paper, we tackle ...

With the rapid development of convolutional neural networks (CNNs), significant progress has been achieved in semantic segmentation. Despite great success, such deep learning approaches require large scale real-world datasets with pixel-level annotations. However, considering that labeling semantics is extremely laborious, many researchers turn to utilize synthetic data free But due clear domai...

In few-shot unsupervised domain adaptation (FS-UDA), most existing methods followed the learning (FSL) to leverage low-level local features (learned from conventional convolutional models, e.g., ResNet) for classification. However, goal of FS-UDA and FSL are relevant yet distinct, since aims classify samples in target rather than source domain. We found that insufficient FS-UDA, which could int...

Approaches towards semantic search can be mainly divided into two kinds: one is augmenting traditional keyword-based search engines with semantic techniques such as ontology, semantic inference; the other is proposing methods for directly searching on semantic repositories as RDF or OWL files. However, compared with those theoretics-driven approaches, semantic search still lacks applications wi...

In this work, we define and address a novel domain adaptation (DA) problem in semantic scene segmentation, where the target not only exhibits data distribution shift w.r.t. source domain, but also includes classes that do exist latter. Different to “open-set” (Panareda Busto Gall, 2017) “universal adaptation” (You et al. 2019), which both regard all objects from new as “unknown”, aim at explici...