More Like this

1. A View-Adversarial Framework for Multi-View Network Embedding

   Dongqi Fu, Zhe Xu (October 2020, CIKM '20: Proceedings of the 29th ACM International Conference on Information & Knowledge)

   null (Ed.)

   Network embedding has demonstrated effective empirical performance for various network mining tasks such as node classification, link prediction, clustering, and anomaly detection. However, most of these algorithms focus on the single-view network scenario. From a real-world perspective, one individual node can have different connectivity patterns in different networks. For example, one user can have different relationships on Twitter, Facebook, and LinkedIn due to varying user behaviors on different platforms. In this case, jointly considering the structural information from multiple platforms (i.e., multiple views) can potentially lead to more comprehensive node representations, and eliminate noises and bias from a single view. In this paper, we propose a view-adversarial framework to generate comprehensive and robust multi-view network representations named VANE, which is based on two adversarial games. The first adversarial game enhances the comprehensiveness of the node representation by discriminating the view information which is obtained from the subgraph induced by neighbors of that node. The second adversarial game improves the robustness of the node representation with the challenging of fake node representations from the generative adversarial net. We conduct extensive experiments on downstream tasks with real-world multi-view networks, which shows that our proposed VANE framework significantly outperforms other baseline methods. 

   more » « less
2. Deep Unsupervised Visual Odometry Via Bundle Adjusted Pose Graph Optimization

   https://doi.org/10.1109/ICRA48891.2023.10160703  

   Lu, Guoyu (May 2023, IEEE International Conference on Robotics and Automation (ICRA))

   Unsupervised visual odometry as an active topic has attracted extensive attention, benefiting from its label-free practical value and robustness in real-world scenarios. However, the performance of camera pose estimation and tracking through deep neural network is still not as ideal as most other tasks, such as detection, segmentation and depth estimation, due to the lack of drift correction in the estimated trajectory and map optimization in the recovered 3D scenes. In this work, we introduce pose graph and bundle adjustment optimization to our network training process, which iteratively updates both the motion and depth estimations from the deep learning network, and enforces the refined outputs to further meet the unsupervised photometric and geometric constraints. The integration of pose graph and bundle adjustment is easy to implement and significantly enhances the training effectiveness. Experiments on KITTI dataset demonstrate that the introduced method achieves a significant improvement in motion estimation compared with other recent unsupervised monocular visual odometry algorithms. 

   more » « less
3. Deep Unsupervised Visual Odometry Via Bundle Adjusted Pose Graph Optimization

   Guoyu Lu (January 2023, IEEE International Conference on Robotics and Automation (ICRA))

   Unsupervised visual odometry as an active topic has attracted extensive attention, benefiting from its label free practical value and robustness in real-world scenarios. However, the performance of camera pose estimation and tracking through deep neural network is still not as ideal as most other tasks, such as detection, segmentation and depth estimation, due to the lack of drift correction in the estimated trajectory and map optimization in the recovered 3D scenes. In this work, we introduce pose graph and bundle adjustment optimization to our network training process, which iteratively updates both the motion and depth estimations from the deep learning network, and enforces the refined outputs to further meet the unsupervised photometric and geometric constraints. The integration of pose graph and bundle adjustment is easy to implement and significantly enhances the training effectiveness. Experiments on KITTI dataset demonstrate that the introduced method achieves a significant improvement in motion estimation compared with other recent unsupervised monocular visual odometry algorithms. 

   more » « less
4. Image-based Process Monitoring via Adversarial Autoencoder with Applications to Rolling Defect Detection

   https://doi.org/10.1109/COASE.2019.8843313  

   Yan, Hao; Yeh, Huai-Ming; Sergin, Nurettin (August 2019, 2019 IEEE 15th International Conference on Automation Science and Engineering)

   null (Ed.)

   Image-based process monitoring has recently attracted increasing attention due to the advancement of the sensing technologies. However, existing process monitoring methods fail to fully utilize the spatial information of images due to their complex characteristics including the high-dimensionality and complex spatial structures. Recent advancements in unsupervised deep models such as generative adversarial networks (GAN) and adversarial autoencoders (AAE) has enabled to learn the complex spatial structures automatically. Inspired by this advancement, we propose an anomaly detection framework based on the AAE for unsupervised anomaly detection for images. AAE combines the power of GAN with the variational autoencoder, which serves as a nonlinear dimension reduction technique. Based on this, we propose a monitoring statistic efficiently capturing the change of the data. The performance of the proposed AAE-based anomaly detection algorithm is validated through a simulation study and real case study for rolling defect detection. 

   more » « less
5. gc DLSeg: integrating graph-cut into deep learning for binary semantic segmentation

   https://doi.org/10.1364/BOE.555206  

   Xie, Hui; Xu, Weiyu; Wang, Ya_Xing; Buatti, John; Wu, Xiaodong (April 2025, Biomedical Optics Express)

   Binary semantic segmentation in computer vision is a fundamental problem. As a model-based segmentation method, the graph-cut approach was one of the most successful binary segmentation methods thanks to its global optimality guarantee of the solutions and its practical polynomial-time complexity. Recently, many deep learning (DL) based methods have been developed for this task and yielded remarkable performance, resulting in a paradigm shift in this field. To combine the strengths of both approaches, we propose in this study to integrate the graph-cut approach into a deep learning network for end-to-end learning. Unfortunately, backward propagation through the graph-cut module in the DL network is challenging due to the combinatorial nature of the graph-cut algorithm. To tackle this challenge, we propose a novel residual graph-cut loss and a quasi-residual connection, enabling the backward propagation of the gradients of the residual graph-cut loss for effective feature learning guided by the graph-cut segmentation model. In the inference phase, globally optimal segmentation is achieved with respect to the graph-cut energy defined on the optimized image features learned from DL networks. Experiments on the public AZH chronic wound data set and the pancreas cancer data set from the medical segmentation decathlon (MSD) demonstrated promising segmentation accuracy and improved robustness against adversarial attacks. 

   more » « less