Zhihao Chen

AAAI Conference 2026 Conference Paper

From Attribution to Action: Jointly ALIGNing Predictions and Explanations

• Dongsheng Hong
• Chao Chen
• Yanhui Chen
• Shanshan Lin
• Zhihao Chen
• Xiangwen Liao

Explanation-guided learning (EGL) has shown promise in aligning model predictions with interpretable reasoning, particularly in computer vision tasks. However, most approaches rely on external annotations or heuristic-based segmentation to supervise model explanations, which can be noisy, imprecise and difficult to scale. In this work, we provide both empirical and theoretical evidence that low-quality supervision signals can degrade model performance rather than improve it. In response, we propose ALIGN, a novel framework that jointly trains a classifier and a masker in an iterative manner. The masker learns to produce soft, task-relevant masks that highlight informative regions, while the classifier is optimized for both prediction accuracy and alignment between its saliency maps and the learned masks. By leveraging high-quality masks as guidance, ALIGN improves both interpretability and generalizability, showing its superiority across various settings. Experiments on the two domain generalization benchmarks, VLCS and Terra Incognita, show that ALIGN consistently outperforms six strong baselines in both in-distribution and out-of-distribution settings. Besides, ALIGN also yields superior explanation quality concerning sufficiency and comprehensiveness, highlighting its effectiveness in producing accurate and interpretable models.

AAAI Conference 2025 Conference Paper

Open-Set Cross-Network Node Classification via Unknown-Excluded Adversarial Graph Domain Alignment

• Xiao Shen
• Zhihao Chen
• Shirui Pan
• Shuang Zhou
• Laurence T. Yang
• Xi Zhou

Existing cross-network node classification methods are mainly proposed for closed-set setting, where the source network and the target network share exactly the same label space. Such a setting is restricted in real-world applications, since the target network might contain additional classes that are not present in the source. In this work, we study a more realistic open-set cross-network node classification (O-CNNC) problem, where the target network contains all the known classes in the source and further contains several target-private classes unseen in the source. Borrowing the concept from open-set domain adaptation, all target-private classes are defined as an additional “unknown” class. To address the challenging O-CNNC problem, we propose an unknown-excluded adversarial graph domain alignment (UAGA) model with a separate-adapt training strategy. Firstly, UAGA roughly separates known classes from unknown class, by training a graph neural network encoder and a neighborhood-aggregation node classifier in an adversarial framework. Then, unknown-excluded adversarial domain alignment is customized to align only target nodes from known classes with the source, while pushing target nodes from unknown class far away from the source, by assigning positive and negative domain adaptation coefficient to known class nodes and unknown class nodes. Extensive experiments on real-world datasets demonstrate significant outperformance of the proposed UAGA over state-of-the-art methods on O-CNNC.

IJCAI Conference 2024 Conference Paper

FLDM-VTON: Faithful Latent Diffusion Model for Virtual Try-on

• Chenhui Wang
• Tao Chen
• Zhihao Chen
• Zhizhong Huang
• Taoran Jiang
• Qi Wang
• Hongming Shan

Despite their impressive generative performance, latent diffusion model-based virtual try-on (VTON) methods lack faithfulness to crucial details of the clothes, such as style, pattern, and text. To alleviate these issues caused by the diffusion stochastic nature and latent supervision, we propose a novel Faithful Latent Diffusion Model for VTON, termed FLDM-VTON. FLDM-VTON improves the conventional latent diffusion process in three major aspects. First, we propose incorporating warped clothes as both the starting point and local condition, supplying the model with faithful clothes priors. Second, we introduce a novel clothes flattening network to constrain generated try-on images, providing clothes-consistent faithful supervision. Third, we devise a clothes-posterior sampling for faithful inference, further enhancing the model performance over conventional clothes-agnostic Gaussian sampling. Extensive experimental results on the benchmark VITON-HD and Dress Code datasets demonstrate that our FLDM-VTON outperforms state-of-the-art baselines and is able to generate photo-realistic try-on images with faithful clothing details.

JBHI Journal 2024 Journal Article

Vital Sign Monitoring for Cancer Patients Based on Dual-Path Sensor and Divided-Frequency-CNN Model

• Bin Lin
• Chuanzheng Jia
• Huicheng Yang
• Yi Zhang
• Xianhe Xie
• Zhihao Chen
• Xianzeng Zhang

Monitoring vital signs is a key part of standard medical care for cancer patients. However, the traditional methods have instability especially when big fluctuations of signals happen, while the deep-learning-based methods lack pertinence to the sensors. A dual-path micro-bend optical fiber sensor and a targeted model based on the Divided-Frequency-CNN (DFC) are developed in this paper to measure the heart rate (HR) and respiratory rate (RR). For each path, features of frequency division based on the mechanism of signal periodicity cooperate with the operation of stable phase extraction to reduce the interference of body movements for monitoring. Then, the DFC model is designed to learn the inner information from the features robustly. Lastly, a weighted strategy is used to estimate the HR and RR via dual paths to increase the anti-interference for errors from one source. The experiments were carried out on the actual clinical data of cancer patients by a hospital. The results show that the proposed method has good performance in error (3. 51 (4. 51 $\%$ ) and 2. 53 (3. 28 $\%$ ) beats per minute (bpm) for cancer patients with pain and without pain respectively), relevance, and consistency with the values from hospital equipment. Besides, the proposed method significantly improved the ability in the report time interval (30 to 9 min), and mean / confidential interval (3. 60/[−22. 61, 29. 81] to −0. 64 / [−9. 21, 7. 92] for patients with pain and 1. 87 / [−5. 49, 9. 23] to −0. 16 / [−6. 21, 5. 89] for patients without pain) compared with our previous work.

JBHI Journal 2023 Journal Article

Uncertainty-Aware Multi-Dimensional Mutual Learning for Brain and Brain Tumor Segmentation

• Junting Zhao
• Zhaohu Xing
• Zhihao Chen
• Liang Wan
• Tong Han
• Huazhu Fu
• Lei Zhu

Existing segmentation methods for brain MRI data usually leverage 3D CNNs on 3D volumes or employ 2D CNNs on 2D image slices. We discovered that while volume-based approaches well respect spatial relationships across slices, slice-based methods typically excel at capturing fine local features. Furthermore, there is a wealth of complementary information between their segmentation predictions. Inspired by this observation, we develop an Uncertainty-aware Multi-dimensional Mutual learning framework to learn different dimensional networks simultaneously, each of which provides useful soft labels as supervision to the others, thus effectively improving the generalization ability. Specifically, our framework builds upon a 2D-CNN, a 2. 5D-CNN, and a 3D-CNN, while an uncertainty gating mechanism is leveraged to facilitate the selection of qualified soft labels, so as to ensure the reliability of shared information. The proposed method is a general framework and can be applied to varying backbones. The experimental results on three datasets demonstrate that our method can significantly enhance the performance of the backbone network by notable margins, achieving a Dice metric improvement of 2. 8% on MeniSeg, 1. 4% on IBSR, and 1. 3% on BraTS2020.

EAAI Journal 2022 Journal Article

DSU-Net: Distraction-Sensitive U-Net for 3D lung tumor segmentation

• Junting Zhao
• Meng Dang
• Zhihao Chen
• Liang Wan