Author name cluster

Jing Liao

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

1 author row

EAAI Journal 2025 Journal Article

Physics-informed neural networks for three-dimensional cerebrovascular hemodynamic prediction: A point cloud preprocessing strategy based on limited data

Jing Liao
Gaoyang Li
Keito Yanagisawa
Shin-Ichiro Sugiyama
Makoto Ohta
Hitomi Anzai

Hemodynamic parameters are crucial for diagnosis and treatment of cerebrovascular diseases, yet real-time, high-resolution, and accurate acquisitions remain challenging due to limitations of current medical imaging and computational techniques. Artificial intelligence (AI)-based hemodynamic prediction also faces data scarcity in clinical settings due to ethical consideration. To address this issue, we aim to enhance learning performance under limited patient datasets with a tailored point cloud preprocessing strategy and a designed neural network architecture. The preprocessing strategy ensures point spatial homogeneity by applying resampling techniques including voxelization and distance-weighted interpolation, optimizing the data derived from computational fluid dynamics (CFD) for AI model training. The physics-informed neural networks (PINNs) module transits the network from a purely data-driven to a semi-data-driven framework, decreasing the data dependency. Four controlled trials were conducted using a limited CFD dataset of 51 patients, with 11 cases reserved for testing, to evaluate the performance of different model combinations, with and without the integration of a PINNs module and point cloud preprocessing. The combined approach showed superior performance in predicting spatially anisotropic hemodynamic fields—including velocity components and pressure—by efficiently mapping spatial coordinates to three-dimensional hemodynamic variables. This method achieved strong visual agreement with CFD simulations while reducing prediction time to 1 s. On the test set, it achieved normalized mean absolute errors of 7. 79 ± 2. 14 % for velocity and 6. 63 ± 2. 80 % for pressure, comparable to previously reported results based on large synthetic datasets. These results demonstrate the method's efficiency, accuracy, and real-time potential for clinical hemodynamic modeling in data-limited scenarios.

Details DOI

JBHI Journal 2025 Journal Article

TDFormer: Top-Down Token Generation for 3D Medical Image Segmentation

Hao Du
Qihua Dong
Yan Xu
Jing Liao

Accurate medical image segmentation is critical to effective treatment strategies. Existing transformer-based methods for image segmentation mostly split the input image into a fixed and regular grid and regard cells in the grid as the vision tokens. However, not all tokens are of equal importance in the medical segmentation tasks, e. g. , the tokens in tumor areas must be processed in a higher resolution than the background tokens which can be easily predicted with fewer transformer layers. In this paper, we propose a simple yet efficient segmentation framework called Top-Down Transformer (TDFormer), which incorporates a spatially adaptive token generation scheme into the transformer. The proposed top-down token generation comprises the following three components: attentiveness calculation, token splitting, and token fusion, where the collaboration of these components gradually fuses redundant background tokens and focuses only on the most critical areas. This allows for allocating more computation to process tokens containing delicate details in a finer resolution. Extensive experiments are conducted to demonstrate the robustness and effectiveness of the proposed TDFormer, that our method are superior to other state-of-the-art methods on the following publicly accessible datasets: BTCV Challenge, LiTS and BraTS 2020. We also dissect our method and evaluate the performance of each component.

Details DOI

NeurIPS Conference 2020 Conference Paper

Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search

Houwen Peng
Hao Du
Hongyuan Yu
Qi Li
Jing Liao
Jianlong Fu

One-shot weight sharing methods have recently drawn great attention in neural architecture search due to high efficiency and competitive performance. However, weight sharing across models has an inherent deficiency, i. e. , insufficient training of subnetworks in the hypernetwork. To alleviate this problem, we present a simple yet effective architecture distillation method. The central idea is that subnetworks can learn collaboratively and teach each other throughout the training process, aiming to boost the convergence of individual models. We introduce the concept of prioritized path, which refers to the architecture candidates exhibiting superior performance during training. Distilling knowledge from the prioritized paths is able to boost the training of subnetworks. Since the prioritized paths are changed on the fly depending on their performance and complexity, the final obtained paths are the cream of the crop. We directly select the most promising one from the prioritized paths as the final architecture, without using other complex search methods, such as reinforcement learning or evolution algorithms. The experiments on ImageNet verify such path distillation method can improve the convergence ratio and performance of the hypernetwork, as well as boosting the training of subnetworks. The discovered architectures achieve superior performance compared to the recent MobileNetV3 and EfficientNet families under aligned settings. Moreover, the experiments on object detection and more challenging search space show the generality and robustness of the proposed method. Code and models are available at \url{https: //github. com/neurips-20/cream. git}.

PDF Details

AAAI Conference 2020 Conference Paper

Model Watermarking for Image Processing Networks

Jie Zhang
DongDong Chen
Jing Liao
Han Fang
Weiming Zhang
Wenbo Zhou
Hao Cui
Nenghai Yu

Deep learning has achieved tremendous success in numerous industrial applications. As training a good model often needs massive high-quality data and computation resources, the learned models often have signiﬁcant business values. However, these valuable deep models are exposed to a huge risk of infringements. For example, if the attacker has the full information of one target model including the network structure and weights, the model can be easily ﬁnetuned on new datasets. Even if the attacker can only access the output of the target model, he/she can still train another similar surrogate model by generating a large scale of input-output training pairs. How to protect the intellectual property of deep models is a very important but seriously under-researched problem. There are a few recent attempts at classiﬁcation network protection only. In this paper, we propose the ﬁrst model watermarking framework for protecting image processing models. To achieve this goal, we leverage the spatial invisible watermarking mechanism. Speciﬁcally, given a black-box target model, a uniﬁed and invisible watermark is hidden into its outputs, which can be regarded as a special task-agnostic barrier. In this way, when the attacker trains one surrogate model by using the input-output pairs of the target model, the hidden watermark will be learned and extracted afterward. To enable watermarks from binary bits to high-resolution images, both traditional and deep spatial invisible watermarking mechanism are considered. Experiments demonstrate the robustness of the proposed watermarking mechanism, which can resist surrogate models learned with different network structures and objective functions. Besides deep models, the proposed method is also easy to be extended to protect data and traditional image processing algorithms.

PDF Details

NeurIPS Conference 2020 Conference Paper

Passport-aware Normalization for Deep Model Protection

Jie Zhang
DongDong Chen
Jing Liao
Weiming Zhang
Gang Hua
Nenghai Yu

Despite tremendous success in many application scenarios, deep learning faces serious intellectual property (IP) infringement threats. Considering the cost of designing and training a good model, infringements will significantly infringe the interests of the original model owner. Recently, many impressive works have emerged for deep model IP protection. However, they either are vulnerable to ambiguity attacks, or require changes in the target network structure by replacing its original normalization layers and hence cause significant performance drops. To this end, we propose a new passport-aware normalization formulation, which is generally applicable to most existing normalization layers and only needs to add another passport-aware branch for IP protection. This new branch is jointly trained with the target model but discarded in the inference stage. Therefore it causes no structure change in the target model. Only when the model IP is suspected to be stolen by someone, the private passport-aware branch is added back for ownership verification. Through extensive experiments, we verify its effectiveness in both image and 3D point recognition models. It is demonstrated to be robust not only to common attack techniques like fine-tuning and model compression, but also to ambiguity attacks. By further combining it with trigger-set based methods, both black-box and white-box verification can be achieved for enhanced security of deep learning models deployed in real systems.

PDF Details

NeurIPS Conference 2019 Conference Paper

Transductive Zero-Shot Learning with Visual Structure Constraint

Ziyu Wan
DongDong Chen
Yan Li
Xingguang Yan
Junge Zhang
Yizhou Yu
Jing Liao

To recognize objects of the unseen classes, most existing Zero-Shot Learning (ZSL) methods first learn a compatible projection function between the common semantic space and the visual space based on the data of source seen classes, then directly apply it to the target unseen classes. However, in real scenarios, the data distribution between the source and target domain might not match well, thus causing the well-known domain shift problem. Based on the observation that visual features of test instances can be separated into different clusters, we propose a new visual structure constraint on class centers for transductive ZSL, to improve the generality of the projection function (\ie alleviate the above domain shift problem). Specifically, three different strategies (symmetric Chamfer-distance, Bipartite matching distance, and Wasserstein distance) are adopted to align the projected unseen semantic centers and visual cluster centers of test instances. We also propose a new training strategy to handle the real cases where many unrelated images exist in the test dataset, which is not considered in previous methods. Experiments on many widely used datasets demonstrate that the proposed visual structure constraint can bring substantial performance gain consistently and achieve state-of-the-art results.

PDF Details