108 citations · 119 across the 7 of their papers we have counts for
7 papers
Mutually Guided Few-shot Learning for Relational Triple Extraction
Chengmei Yang, Shuai Jiang, Bowei He +2
Knowledge graphs (KGs), containing many entity-relation-entity triples, provide rich information for downstream applications. Although extracting triples from unstructured texts ha…
Unsupervised Adaptive Semantic Segmentation with Local Lipschitz Constraint
Guanyu Cai, Lianghua He
Recent advances in unsupervised domain adaptation have seen considerable progress in semantic segmentation. Existing methods either align different domains with adversarial trainin…
Segmenting Medical MRI via Recurrent Decoding Cell
Ying Wen, Kai Xie, Lianghua He
The encoder-decoder networks are commonly used in medical image segmentation due to their remarkable performance in hierarchical feature fusion. However, the expanding path for fea…
Adaptive Routing Between Capsules
Qiang Ren, Shaohua Shang, Lianghua He
Capsule network is the most recent exciting advancement in the deep learning field and represents positional information by stacking features into vectors. The dynamic routing algo…
Learning Smooth Representation for Unsupervised Domain Adaptation
Guanyu Cai, Lianghua He, Mengchu Zhou +2
Typical adversarial-training-based unsupervised domain adaptation methods are vulnerable when the source and target datasets are highly-complex or exhibit a large discrepancy betwe…
Virtual Conditional Generative Adversarial Networks
Haifeng Shi, Guanyu Cai, Yuqin Wang +2
When trained on multimodal image datasets, normal Generative Adversarial Networks (GANs) are usually outperformed by class-conditional GANs and ensemble GANs, but conditional GANs…
Unsupervised Domain Adaptation with Adversarial Residual Transform Networks
Guanyu Cai, Yuqin Wang, Mengchu Zhou +1
Domain adaptation is widely used in learning problems lacking labels. Recent studies show that deep adversarial domain adaptation models can make markable improvements in performan…