Most visual recognition methods implicitly assume the data distribution remains unchanged from training to testing. However, in practice domain shift often exists, where real-world factors such as lighting and sensor type change between train and test, and classifiers do not generalise from source to target domains. It is impractical to train separate models for all possible situations because ...

We are interested in improving the summarization of conversations by using domain adaptation. Since very few email corpora have been annotated for summarization purposes, we attempt to leverage the labeled data available in the multiparty meetings domain for the summarization of email threads. In this paper, we compare several approaches to supervised domain adaptation using out-ofdomain labele...

Intra-domain and inter-domain gaps are widely presented in image processing tasks due to data distribution differences. In the field of dehazing, particular previous works have paid attention gap between synthetic domain real domain. However, those methods only establish connection from without considering significant shift within (intra-domain gap). this work, we propose a Two-Step Dehazing Ne...

Real-world robotics problems often occur in domains that differ significantly from the robot’s prior training environment. For many robotic control tasks, real world experience is expensive to obtain, but data is easy to collect in either an instrumented environment or in simulation. We propose a novel domain adaptation approach for robot perception that adapts visual representations learned on...

We present a novel multiple-source unsupervised model for text classification under domain shift. Our exploits the update rates in document representations to dynamically integrate encoders. It also employs probabilistic heuristic infer error rate target order pair source classifiers. data transformation cost and classifier accuracy feature space. have used real world scenarios of Domain Adapta...

Domain adaptation aims to leverage a label-rich domain (the source domain) help model learning in label-scarce target domain). Most methods require the co-existence of and samples reduce distribution mismatch. However, access may not always be feasible real-world applications due different problems ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlin...