Yizhou Wang

Yizhou Wang

Auto-generated profile, based on publicly available information

Yizhou Wang

Northeastern University, Boston, USA and Adobe, Seattle, USA

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
19 January 2022 in Nature Communications
Verified
Journal Article
Open access
PDF file
CDChangyu Deng
Changyu Deng
YWYizhou Wang
Yizhou Wang
CQCan Qin
Can Qin
YFYun Fu
Yun Fu
WLWei Lu
Wei Lu
Topology optimization by optimally distributing materials in a given domain requires non-gradient optimizers to solve highly complicated problems. However, with hundreds of design variables or more involved, solving such problems would require millions of Finite Element Method (FEM) calculations whose computational cost is huge and impractical. Here we report Self-directed Online Learning Optimization (SOLO) which integrates Deep Neural Network (DNN) with FEM calculations. A DNN learns and substitutes the objective as a function of design variables. A small number of training data is generated dynamically based on the DNN’s prediction of the optimum. The DNN adapts to the new training data and gives better prediction in the region of interest until convergence. The optimum predicted by the DNN is proved to converge to the true global optimum through iterations. Our algorithm was tested by four types of problems including compliance minimization, fluid-structure optimization, heat transfer enhancement and truss optimization. It reduced the computational time by 2 ~ 5 orders of magnitude compared with directly using heuristic methods, and outperformed all state-of-the-art algorithms tested in our experiments. This approach enables solving large multi-dimensional optimization problems.

23 August 2024 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
YWYizhou Wang
Yizhou Wang
CQCan Qin
Can Qin
RWRongzhe Wei
Rongzhe Wei
YXYi Xu
Yi Xu
YBYue Bai
Yue Bai
YFYun Fu
Yun Fu
Anomaly detection is a fundational yet difficult problem in machine learning. In this work, we propose a new and effective framework, dubbed as SLA $^{2}$ P, for unsupervised anomaly detection. Following the extraction of delegate embeddings from raw data, we implement random projections on the features and consider features transformed by disparate projections as being associated with separate pseudo-classes. We then train a neural network for classification on these transformed features to conduct self-supervised learning. Subsequently, we introduce adversarial disturbances to the modified attributes, and we develop anomaly scores built on the classifier's predictive uncertainties concerning these disrupted features. Our approach is motivated by the fact that as anomalies are relatively rare and decentralized, 1) the training of the pseudo-label classifier concentrates more on acquiring the semantic knowledge of regular data instead of anomalous data; 2) the altered attributes of the normal data exhibit greater resilience to disturbances compared to those of the anomalous data. Therefore, the disrupted modified attributes of anomalies can not be well classified and correspondingly tend to attain lesser anomaly scores. The results of experiments on various benchmark datasets for images, text, and inherently tabular data demonstrate that SLA $^{2}$ P achieves state-of-the-art performance consistently.

6 September 2023 in SIAM Journal on Imaging Sciences
Verified
Journal Article
Closed access
YYYan Yang
Yan Yang
YWYizhou Wang
Yizhou Wang
JWJiazhen Wang
Jiazhen Wang
JSJian Sun
Jian Sun
ZXZongben Xu
Zongben Xu
Parallel imaging (PI), relying on multicoils to sense [Formula: see text]-space data, is an effective technique to accelerate magnetic resonance imaging by exploiting spatial sensitivity coding of multiple coils, with an integrated compressive sensing (CS) technology to achieve higher acceleration. In this paper, we propose a novel nonconvex reconstruction model and its proximal alternating linearized minimization (PALM) algorithm for PI in a blind setting that MR image and multichannel sensitivity maps are jointly estimated, regularized by image and sensitivity regularizers. Instead of hand-crafting the image and sensitivity regularizers, we propose unrolling the PALM algorithm to be a deep network for Blind Parallel MRI, dubbed as BPMRI-Net, with two learnable subnetworks to substitute the proximal operators of the image and sensitivity regularizers. We theoretically prove the linear convergence of BPMRI-Net as an iterative algorithm, which alternately updates two variables based on the learnable proximal operators. The learned BPMRI-Net can simultaneously output the MR image and sensitivity maps from undersampled multichannel [Formula: see text]-space data even when the number of low-frequency sampling lines in the center of [Formula: see text]-space is small. Numerical results demonstrate the effectiveness of our method with state-of-the-art reconstruction accuracy.

25 January 2021 in Research Square
Verified
Preprint
Open access
PDF file
CDChangyu Deng
Changyu Deng
YWYizhou Wang
Yizhou Wang
CQCan Qin
Can Qin
WLWei Lu
Wei Lu
Topology optimization by optimally distributing materials in a given domain requires gradient-free optimizers to solve highly complicated problems. However, with hundreds of design variables or more involved, solving such problems would require millions of Finite Element Method (FEM) calculations whose computational cost is huge and impractical. Here we report a Self-directed Online Learning Optimization (SOLO) which integrates Deep Neural Network (DNN) with FEM calculations. A DNN learns and substitutes the objective as a function of design variables. A small number of training data is generated dynamically based on the DNN's prediction of the global optimum. The DNN adapts to the new training data and gives better prediction in the region of interest until convergence. Our algorithm was tested by compliance minimization problems and fluid-structure optimization problems. It reduced the computational time by 2 ~ 5 orders of magnitude compared with directly using heuristic methods, and outperformed all state-of-the-art algorithms tested in our experiments. This approach enables solving large multi-dimensional optimization problems.

19 July 2026
Verified
Conference Paper
Open access
JZJingdong Zhang
Jingdong Zhang
XZXiaohang Zhan
Xiaohang Zhan
LZLingzhi Zhang
Lingzhi Zhang
YWYizhou Wang
Yizhou Wang
ZYZhengming Yu
Zhengming Yu
Xin LiXin Li
Xin Li
Comprehensive panoramic scene understanding is critical for immersive applications, yet it remains challenging due to the scarcity of high-resolution, multi-task annotations. While perspective foundation models have achieved success through data scaling, directly adapting them to the panoramic domain often fails due to severe geometric distortions and coordinate system discrepancies. Furthermore, the underlying relations between diverse dense prediction tasks in spherical spaces are underexplored. To address these challenges, we propose MTPano, a robust multi-task panoramic foundation model established by a label-free training pipeline. First, to circumvent data scarcity, we leverage powerful perspective dense priors. We project panoramic images into perspective patches to generate accurate, domain-gap-free pseudo-labels using off-the-shelf foundation models, which are then re-projected to serve as patch-wise supervision. Second, to tackle the interference between task types, we categorize tasks into rotation-invariant (e.g., depth, segmentation) and rotation-variant (e.g., surface normals) groups. We introduce the Panoramic Dual BridgeNet (PD-BridgeNet), which disentangles these feature streams via geometry-aware modulation layers that inject absolute position and ray direction priors. To handle the distortion from equirectangular projections (ERP), we incorporate ERP token mixers followed by a dual-branch BridgeNet for interactions with gradient truncation, facilitating beneficial cross-task information sharing while blocking conflicting gradients from incompatible task attributes. Additionally, we introduce auxiliary tasks (image gradient, edge distance field, point map estimation) to fertilize the cross-task learning process. Extensive experiments demonstrate that MTPano achieves state-of-the-art performance on multiple benchmarks and delivers competitive results against task-specific panoramic specialist foundation models. Code and model is released at https://github.com/Evergreen0929/MTPano.