Text-to-image generative models can produce diverse high-quality images ...
Room layout estimation predicts layouts from a single panorama. It requi...
Deep learning-based diagnostic system has demonstrated potential in
clas...
Mixup-based data augmentation has been validated to be a critical stage ...
Many research efforts have been committed to unsupervised domain adaptat...
Domain adaptation (DA) aims to transfer the knowledge of a well-labeled
...
To interpret deep models' predictions, attention-based visual cues are w...
Nuclear norm maximization has shown the power to enhance the transferabi...
Prediction of pedestrian behavior is critical for fully autonomous vehic...
Detecting navigable space is a fundamental capability for mobile robots
...
Open-set domain adaptation (OSDA) considers that the target domain conta...
Domain adaptation has received a lot of attention in recent years, and m...
Weakly-supervised learning has attracted growing research attention on
m...
Domain adaptation (DA) becomes an up-and-coming technique to address the...
Unsupervised Domain adaptation (UDA) attempts to recognize the unlabeled...
Partial domain adaptation (PDA) attracts appealing attention as it deals...
Partial domain adaptation aims to adapt knowledge from a larger and more...
Heterogeneous domain adaptation (HDA) transfers knowledge across source ...
Existing domain adaptation methods aim to reduce the distributional
diff...
Unsupervised domain adaptation targets to transfer task knowledge from
l...
Tremendous research efforts have been made to thrive deep domain adaptat...
Domain Adaptation (DA) aims to generalize the classifier learned from th...
Deep domain adaptation methods have achieved appealing performance by
le...
Nowadays, with the rapid development of data collection sources and feat...
Domain Adaptation (DA) targets at adapting a model trained over the
well...
Unsupervised domain adaptation facilitates the unlabeled target domain
r...
Many domain adaptation (DA) methods aim to project the source and target...
It is always an attractive task to discover knowledge for various learni...
Domain adaptation investigates the problem of cross-domain knowledge tra...
Consensus clustering fuses diverse basic partitions (i.e., clustering re...
Conventional zero-shot learning (ZSL) methods generally learn an embeddi...
Person re-identification (re-ID) has recently been tremendously boosted ...