Wenwei Zhang

Wenwei Zhang

Auto-generated profile, based on publicly available information

Wenwei Zhang

Shanghai AI Laboratory, Shanghai, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 May 2025
Verified
Book Chapter
Closed access
PDF file
SZShilong Zhang
Shilong Zhang
PSPeize Sun
Peize Sun
SCShoufa Chen
Shoufa Chen
MXMin Xiao
Min Xiao
WSWenqi Shao
Wenqi Shao
Ping LuoPing Luo
Ping Luo

29 July 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Open access
Xiangtai LiXiangtai Li
Xiangtai Li
HDHenghui Ding
Henghui Ding
HYHaobo Yuan
Haobo Yuan
WZWenwei Zhang
Wenwei Zhang
JPJiangmiao Pang
Jiangmiao Pang
CLChen Change Loy
Chen Change Loy
Visual segmentation seeks to partition images, video frames, or point clouds into multiple segments or groups. This technique has numerous real-world applications, such as autonomous driving, image editing, robot sensing, and medical analysis. Over the past decade, deep learning-based methods have made remarkable strides in this area. Recently, transformers, a type of neural network based on self-attention originally designed for natural language processing, have considerably surpassed previous convolutional or recurrent approaches in various vision processing tasks. Specifically, vision transformers offer robust, unified, and even simpler solutions for various segmentation tasks. This survey provides a thorough overview of transformer-based visual segmentation, summarizing recent advancements. We first review the background, encompassing problem definitions, datasets, and prior convolutional methods. Next, we summarize a meta-architecture that unifies all recent transformer-based approaches. Based on this meta-architecture, we examine various method designs, including modifications to the meta-architecture and associated applications. We also present several specific subfields, including 3D point cloud segmentation, foundation model tuning, domain-aware segmentation, efficient segmentation, and medical segmentation. Additionally, we compile and re-evaluate the reviewed methods on several well-established datasets. Finally, we identify open challenges in this field and propose directions for future research. The project page can be found at https://github.com/lxtGH/Awesome-Segmentation-With-Transformer .

1 October 2019
Verified
Conference Paper
Closed access
WZWenwei Zhang
Wenwei Zhang
HZHui Zhou
Hui Zhou
SSShuyang Sun
Shuyang Sun
ZWZhe Wang
Zhe Wang
JSJianping Shi
Jianping Shi
CLChen Change Loy
Chen Change Loy

29 October 2020
Verified
Book Chapter
Closed access
PDF file
JWJiaqi Wang
Jiaqi Wang
WZWenwei Zhang
Wenwei Zhang
YCYuhang Cao
Yuhang Cao
KCKai Chen
Kai Chen
JPJiangmiao Pang
Jiangmiao Pang
DLDahua Lin
Dahua Lin

1 June 2020
Verified
Conference Paper
Closed access
DZDongzhan Zhou
Dongzhan Zhou
XZXinchi Zhou
Xinchi Zhou
WZWenwei Zhang
Wenwei Zhang
CLChen Change Loy
Chen Change Loy
SYShuai Yi
Shuai Yi
WOWanli Ouyang
Wanli Ouyang
Neural Architecture Search (NAS) achieves significant progress in many computer vision tasks. While many methods are proposed to improve the efficiency of NAS, the search progress is still laborious because training and evaluating plausible architectures over large search space is time-consuming. Assessing network candidates under a proxy (i.e., computationally reduced setting) thus becomes inevitable. In this paper, we observe that most existing proxies exhibit different behaviors in maintaining the rank consistency among network candidates. In particular, some proxies can be more reliable – the rank of candidates does not differ much comparing their reduced setting performance and final performance. In this paper, we systematically investigate some widely adopted reduction factors and report our observations. Inspired by these observations, we present a reliable proxy and further formulate a hierarchical proxy strategy that spends more computations on candidate networks that are potentially more accurate, while discards unpromising ones in early stage with a fast proxy. This leads to an economical evolutionary-based NAS (EcoNAS), which achieves an impressive 400×search time reduction in comparison to the evolutionary-based state of the art [19] (8 v.s. 3150 GPU days). Some new proxies led by our observations can also be applied to accelerate other NAS methods while still able to discover good candidate networks with performance matching those found by previous proxy strategies. Codes and models will be released to facilitate future research.

28 January 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
LKLingdong Kong
Lingdong Kong
XXXiang Xu
Xiang Xu
JRJiawei Ren
Jiawei Ren
WZWenwei Zhang
Wenwei Zhang
LPLiang Pan
Liang Pan
ZLZiwei Liu
Ziwei Liu
Efficient data utilization is crucial for advancing 3D scene understanding in autonomous driving, where reliance on heavily human-annotated LiDAR point clouds challenges fully supervised methods. Addressing this, our study extends into semi-supervised learning for LiDAR semantic segmentation, leveraging the intrinsic spatial priors of driving scenes and multi-sensor complements to augment the efficacy of unlabeled datasets. We introduce LaserMix++, an evolved framework that integrates laser beam manipulations from disparate LiDAR scans and incorporates LiDAR-camera correspondences to further assist data-efficient learning. Our framework is tailored to enhance 3D scene consistency regularization by incorporating multi-modality, including 1) multi-modal LaserMix operation for fine-grained cross-sensor interactions; 2) camera-to-LiDAR feature distillation that enhances LiDAR feature learning; and 3) language-driven knowledge guidance generating auxiliary supervisions using open-vocabulary models. The versatility of LaserMix++ enables applications across LiDAR representations, establishing it as a universally applicable solution. Our framework is rigorously validated through theoretical analysis and extensive experiments on popular driving perception datasets. Results demonstrate that LaserMix++ markedly outperforms fully supervised alternatives, achieving comparable accuracy with five times fewer annotations and significantly improving the supervised-only baselines. This substantial advancement underscores the potential of semi-supervised approaches in reducing the reliance on extensive labeled data in LiDAR-based 3D scene understanding systems.