In this paper, we propose a cascaded non-local neural network for point cloud segmentation. The proposed network aims to build the long-range dependencies of point clouds for the accurate segmentation. Specifically, w...
详细信息
Reweighting adversarial data during training has been recently shown to improve adversarial robustness, where data closer to the current decision boundaries are regarded as more critical and given larger weights. Howe...
详细信息
作者：
Zheng, RuishenXie, JinQian, JianjunYang, JianPCA Lab
Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China
How to measure the similarity of samples is a fundamental problem in many computervision tasks such as retrieval and clustering. Due to the rapid development of deep neural networks, deep metric learning has been wid...
详细信息
作者：
Cheng, XiFu, ZhenyongYang, JianPCA Lab
Key Lab of Intelligent Percept. and Syst. for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China
The prevalence of digital sensors, such as digital cameras and mobile phones, simplifies the acquisition of photos. Digital sensors, however, suffer from producing Moire when photographing objects having complex textu...
详细信息
Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computervision and pattern recognition, and underpins a diverse set of real-world applications. The task of FGIA targets analyzing visua...
详细信息
Reweighting adversarial data during training has been recently shown to improve adversarial robustness, where data closer to the current decision boundaries are regarded as more critical and given larger weights. Howe...
ISBN:
(纸本)9781713845393
Reweighting adversarial data during training has been recently shown to improve adversarial robustness, where data closer to the current decision boundaries are regarded as more critical and given larger weights. However, existing methods measuring the closeness are not very reliable: they are discrete and can take only a few values, and they are path-dependent, i.e., they may change given the same start and end points with different attack paths. In this paper, we propose three types of probabilistic margin (PM), which are continuous and path-independent, for measuring the aforementioned closeness and reweighting adversarial data. Specifically, a PM is defined as the difference between two estimated class-posterior probabilities, e.g., such a probability of the true label minus the probability of the most confusing label given some natural data. Though different PMs capture different geometric properties, all three PMs share a negative correlation with the vulnerability of data: data with larger/smaller PMs are safer/riskier and should have smaller/larger weights. Experiments demonstrated that PMs are reliable and PM-based reweighting methods outperformed state-of-the-art counterparts.
Landmark/pose estimation in single monocular images has received much effort in computervision due to its important applications. It remains a challenging task when input images come with severe occlusions caused by,...
详细信息
Landmark/pose estimation in single monocular images has received much effort in computervision due to its important applications. It remains a challenging task when input images come with severe occlusions caused by, e.g., adverse camera views. Under such circumstances, biologically implausible pose predictions may be produced. In contrast, human vision is able to predict poses by exploiting geometric constraints of landmark point inter-connectivity. To address the problem, by incorporating priors about the structure of pose components, we propose a novel structure-aware fully convolutional network to implicitly take such priors into account during training of the deep network. Explicit learning of such constraints is typically challenging. Instead, inspired by how human identifies implausible poses, we design discriminators to distinguish the real poses from the fake ones (such as biologically implausible ones). If the pose generator G generates results that the discriminator fails to distinguish from real ones, the network successfully learns the priors. Training of the network follows the strategy of conditional Generative Adversarial Networks (GANs). The effectiveness of the proposed network is evaluated on three pose-related tasks: 2D human pose estimation, 2D facial landmark estimation and 3D human pose estimation. The proposed approach significantly outperforms several state-of-the-art methods and almost always generates plausible pose predictions, demonstrating the usefulness of implicit learning of structures using GANs.
Person Search is a practically relevant task that aims to jointly solve Person Detection and Person Re-identification (re-ID). Specifically, it requires to find and locate all instances with the same identity as the q...
详细信息
ISBN:
(数字)9781728171685
ISBN:
(纸本)9781728171692
Person Search is a practically relevant task that aims to jointly solve Person Detection and Person Re-identification (re-ID). Specifically, it requires to find and locate all instances with the same identity as the query person in a set of panoramic gallery images. One major challenge comes from the contradictory goals of the two sub-tasks, i.e., person detection focuses on finding the commonness of all persons while person re-ID handles the differences among multiple identities. Therefore, it is crucial to reconcile the relationship between the two sub-tasks in a joint person search model. To this end, We present a novel approach called Norm-Aware Embedding to disentangle the person embedding into norm and angle for detection and re-ID respectively, allowing for both effective and efficient multi-task training. We further extend the proposal-level person embedding to pixel-level, whose discrimination ability is less affected by mis-alignment. We outperform other one-step methods by a large margin and achieve comparable performance to two-step methods on both CUHK-SYSU and PRW. Also, Our method is easy to train and resource-friendly, running at 12 fps on a single GPU.
WebFG 2020 is an international challenge hosted by Nanjing University of Science and Technology, University of Edinburgh, Nanjing University, The University of Adelaide, Waseda University, etc. This challenge mainly p...
详细信息
According to the unique characteristics of terahertz (THz) waves, THz imaging has become a hot topic in widely application areas. However, the imaging resolution is constrained by its long wavelength. Generally, the d...
详细信息
暂无评论