activity
20192023
most citedBiFormer: Vision Transformer with Bi-Level Routing Attention

67 citations · 69 across the 3 of their papers we have counts for

collaborators
Showing cs.CVShow all

5 papers · 1 filter

cs.CV2023★ 1 cited

Distribution Aligned Diffusion and Prototype-guided network for Unsupervised Domain Adaptive Segmentation

Haipeng Zhou, Lei Zhu, Yuyin Zhou

The Diffusion Probabilistic Model (DPM) has emerged as a highly effective generative model in the field of computer vision. Its intermediate latent vectors offer rich semantic info…

cs.CV2023★ 67 cited

BiFormer: Vision Transformer with Bi-Level Routing Attention

Lei Zhu, Xinjiang Wang, Zhanghan Ke +2

As the core building block of vision transformers, attention is a powerful tool to capture long-range dependency. However, such power comes at a cost: it incurs a huge computation…

cs.CV2023★ 1 cited

GeoSpark: Sparking up Point Cloud Segmentation with Geometry Clue

Zhening Huang, Xiaoyang Wu, Hengshuang Zhao +4

Current point cloud segmentation architectures suffer from limited long-range feature modeling, as they mostly rely on aggregating information with local neighborhoods. Furthermore…

cs.CV2021

MT-ORL: Multi-Task Occlusion Relationship Learning

Panhe Feng, Qi She, Lei Zhu +7

Retrieving occlusion relation among objects in a single image is challenging due to sparsity of boundaries in image. We observe two key issues in existing works: firstly, lack of a…

cs.CV2019

DDNet: Dual-path Decoder Network for Occlusion Relationship Reasoning

Panhe Feng, Xuejing Kang, Lizhu Ye +3

Occlusion relationship reasoning based on convolution neural networks consists of two subtasks: occlusion boundary extraction and occlusion orientation inference. Due to the essent…