YWYongjian Wu

Yongjian Wu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Yongjian Wu has a total of 23 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Learning Occlusion Disentanglement with Fine-grained Localization for Occluded Person Re-identification

    by Wenfeng Liu, Xudong Wang, Lei Tan, Yan Zhang, Pingyang Dai, Yongjian We, Rongrong Ji

    Person re-identification (Re-ID) has been extensively investigated in recent years. However, many existing paradigms rely on holistic person regions for matching, disregarding the challenges posed by occlusions in real-world scenarios. Recent methods have explored occlusion augmentation or external semantic cues. Nevertheless, these approaches tend to be coarse-grained, discarding valuable semantic information in local regions when determining them as occlusions. In this paper, we propose a Fine-grained Occlusion Disentanglement Network (FODN) that can extract more information from limited person regions. Specifically, we propose a fine-grained occlusion augmentation scheme to generate diverse occlusion data and employ bilinear interpolation and downsampling strategies to obtain fine-grained occlusion labels. We then design an occlusion feature disentanglement Module that decouples norm and angle from features and supervises the occlusion-aware task using the aforementioned occlusion labeling and person re-identification tasks, respectively, resulting in more robust features. Additionally, we propose a dynamic local weight controller to balance the relative importance of various human body parts, thereby improving the model's ability to mine more effective local features from limited human body regions after occlusion removal. Comprehensive experiments on various person Re-ID benchmarks demonstrate the superiority of FODN over state-of-the-art methods.


  • Open Access

    Dynamic Prototype Mask for Occluded Person Re-Identification

    by Lei Tan, Pingyang Dai, Rongrong Ji, Yongjian Wu

    Although person re-identification has achieved an impressive improvement in recent years, the common occlusion case caused by different obstacles is still an unsettled issue in real application scenarios. Existing methods mainly address this issue by employing body clues provided by an extra network to distinguish the visible part. Nevertheless, the inevitable domain gap between the assistant model and the ReID datasets has highly increased the difficulty to obtain an effective and efficient model. To escape from the extra pre-trained networks and achieve an automatic alignment in an end-to-end trainable network, we propose a novel Dynamic Prototype Mask (DPM) based on two self-evident prior knowledge. Specifically, we first devise a Hierarchical Mask Generator which utilizes the hierarchical semantic to select the visible pattern space between the high-quality holistic prototype and the feature representation of the occluded input image. Under this condition, the occluded representation could be well aligned in a selected subspace spontaneously. Then, to enrich the feature representation of the high-quality holistic prototype and provide a more complete feature space, we introduce a Head Enrich Module to encourage different heads to aggregate different patterns representation in the whole image. Extensive experimental evaluations conducted on occluded and holistic person re-identification benchmarks demonstrate the superior performance of the DPM over the state-of-the-art methods. The code is released at https://github.com/stone96123/DPM.

  • Open Access

    Contextual Level-Set Method for Breast Tumor Segmentation

    by Sumaira Hussain, Xiaoming Xi, Inam Ullah, Yongjian Wu, Chunxiao Ren, Zhao Lianzheng, Cuihuan Tian, Yilong Yin

    Breast ultrasound image segmentation is the foundation of the diagnosis and treatment of breast cancer. The level set method is widely used for medical image segmentation. However, it remained a challenge for traditional level set methods because they cannot fully understand the tumor regions with complex characteristics by only low-level features. Considering that contextual features can provide complementary discriminative information to low-level features, this paper proposed a contextual level set method for breast tumor segmentation. Firstly, an encoder-decoder architecture network such as UNet is developed to learn high-level contextual features with semantic information. After that, the contextual level set method has been proposed to incorporate the novel contextual energy term. The proposed term has the ability to embed the high-level contextual knowledge into the level set framework. The learned contextual features with semantic information can provide more discriminative information, which has been directly associated with category labels, instead of the original intensity. Therefore, it is robust to serious intensity inhomogeneity, which is helpful to improve segmentation performance. The experiments had taken place with the help of three databases, which indicates that the proposed method outperformed traditional methods.


  • Open Access

    Correction Learning for Medical Image Segmentation

    by Guang Zhang, Shuhao Dong, Hui Xu, Hongyu Zhang, Yongjian Wu, Yanwei Zhang, Xiaoming Xi, Yilong Yin

    Breast tumor segmentation is useful to diagnose breast cancer. However, challenges, such as intensity inhomogeneity and shadowing artifacts arise in this task. To address these two issues, this paper proposes a robust ultrasound image segmentation method based on correction learning. At first, a novel idea of correction learning is introduced. In contrast to traditional methods that develop the complex models to obtain accurate segmentation results, correction learning aims to detect the erroneous segmentation in advance and correct this automatically by only using simple method. The proposed correction learning method mainly involves two steps: coarse segmentation and correction learning. First, an active contour model is firstly constructed for coarse segmentation by introducing assumption of bias field and local intensity clustering property. Then, correction learning is developed to address the erroneous segmentation and to improve the segmentation performance. In this paper, correction learning mainly contains Internal Tumor Block Correction (ITBC) and Boundary Block Correction(BBC). In order to correct the erroneous segmentation caused by intensity inhomogeneity, the internal tumor blocks detection model based on Simple Linear Iterative Clustering(SLIC) and Support Vector Machine (SVM) is learned to detect these segmented blocks. Based on the detection result, the incorrect segmented blocks can be corrected. In addition, BBC is proposed to correct the erroneous segmentation of boundary blocks which are caused by shadowing artifacts. Our experiment results on the constructed database demonstrate the effectiveness and robustness of the proposed method.


  • Open Access

    Label-Distribution Learning-Embedded Active Contour Model for Breast Tumor Segmentation

    by Yongjian Wu, Xiaoming Xi, Xianjing Meng, Xiushan Nie, Yanwei Ren, Guang Zhang, Cuihuan Tian, Yilong Yin

    Tumor segmentation is the foundation of breast ultrasound image analysis. However, intensity inhomogeneity occurred in ultrasound images results in the ambiguous segmentation. In order to tackle the challenge, this paper proposed label-distribution learning embedded active contour model for the breast tumor segmentation. Considering that reasonable exploitation of label ambiguity may help to improve performance, a deep pixel-wise label distribution learning model is first proposed to learn an ambiguous label map. The learned map is independent on the intensity variation, which is robust to the intensity inhomogeneity. After that, a novel label distribution learning embedded active contour model is proposed. The new energy function is developed by introducing the new label distribution fitting energy into the active contour model framework. The proposed new fitting energy can enforce the label of pixels to be similar to the learned distribution map, which improves the robustness to the intensity inhomogeneity. To demonstrate the effectiveness of the proposed method, we conduct the experiment on the breast ultrasound images database which consists of 135 benign cases and 51 malignant cases. Our experimental results demonstrated that the proposed method outperforms the state of the art.