most citedDecompose to Adapt: Cross-domain Object Detection via Feature Disentanglement

2 citations · 3 across the 7 of their papers we have counts for

collaborators

8 papers

cs.CV2022

Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds

Heng Wang, Chaoyi Zhang, Jianhui Yu +1

Dense captioning in 3D point clouds is an emerging vision-and-language task involving object-level 3D scene understanding. Apart from coarse semantic class prediction and bounding…

cs.CV2022

Towards Bi-directional Skip Connections in Encoder-Decoder Architectures and Beyond

Tiange Xiang, Chaoyi Zhang, Xinyi Wang +4

U-Net, as an encoder-decoder architecture with forward skip connections, has achieved promising results in various medical image analysis tasks. Many recent approaches have also ex…

cs.CV2022

SupWMA: Consistent and Efficient Tractography Parcellation of Superficial White Matter with Deep Learning

Tengfei Xue, Fan Zhang, Chaoyi Zhang +6

White matter parcellation classifies tractography streamlines into clusters or anatomically meaningful tracts to enable quantification and visualization. Most parcellation methods…

cs.CV20222 cited

Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglement

Dongnan Liu, Chaoyi Zhang, Yang Song +4

Recent advances in unsupervised domain adaptation (UDA) techniques have witnessed great success in cross-domain computer vision tasks, enhancing the generalization ability of data-…

eess.IV2021

Voxel-wise Cross-Volume Representation Learning for 3D Neuron Reconstruction

Heng Wang, Chaoyi Zhang, Jianhui Yu +4

Automatic 3D neuron reconstruction is critical for analysing the morphology and functionality of neurons in brain circuit activities. However, the performance of existing tracing a…

cs.CV2021

Deep Fiber Clustering: Anatomically Informed Unsupervised Deep Learning for Fast and Effective White Matter Parcellation

Yuqian Chen, Chaoyi Zhang, Yang Song +5

White matter fiber clustering (WMFC) enables parcellation of white matter tractography for applications such as disease classification and anatomical tract segmentation. However, t…