Search

3D deep learning has been increasingly more popular for a variety of tasks including many safety-critical applications. However, recently several works raise the security issues of 3D deep models. Although most of them consider adversarial attacks, we identify that backdoor attack is indeed a more serious threat to 3D deep learning systems but remains unexplored. We present the backdoor attacks in 3D point cloud with a unified framework that exploits the unique properties of 3D data and networks. In particular, we design two attack approaches on point cloud: the poison-label backdoor attack (PointPBA) and the clean-label backdoor attack (PointCBA). The first one is straightforward and effective in practice, while the latter is more sophisticated assuming there are certain data inspections. The attack algorithms are mainly motivated and developed by 1) the recent discovery of 3D adversarial samples suggesting the vulnerability of deep models under spatial transformation; 2) the proposed feature disentanglement technique that manipulates the feature of the data through optimization methods and its potential to embed a new task. Extensive experiments show the efficacy of the PointPBA with over 95% success rate across various 3D datasets and models, and the more stealthy PointCBA with around 50% success rate. Our proposed backdoor attack in 3D point cloud is expected to perform as a baseline for improving the robustness of 3D deep models., Comment: Accepted by ICCV 2021

Despite much effort has been devoted to skin lesion segmentation, the performance of existing methods is still not satisfactory enough for practical applications. The challenges may include fuzzy lesion boundary, uneven and low contrast, and variation of colors across space, which often lead to fragmentary segmentation and inaccurate boundary. To alleviate this problem, we propose a multi-scale context-guided network named as MSCGnet to segment the skin lesions accurately. In MSCGnet, the context information is utilized to guide the feature encoding procedure. Moreover, because of the information loss in spatial down-sampling, a context-based attention structure (CAs) is designed to select effective context features in the decoding path. Furthermore, we boost the performance of MSCGnet with iterations and term this upgraded version as iterative MSCGnet, denoted as iMSCGnet. To supervise the training of iMSCGnet in an end-to-end fashion, a novel objective function of deep supervision, which consists of the terms of each encoding layers and the terms from each MSCGnet output of iMSCGnet, is employed. Our method is evaluated extensively on the four publicly available datasets, including ISBI2016 [1] , ISBI2017 [2] , ISIC2018 [3] and PH2 [4] datasets. The experimental results prove the effectiveness of proposed components and show that our method generally outperforms the state-of-the-art methods.

To facilitate depth-based 3D action recognition, 3D dynamic voxel (3DV) is proposed as a novel 3D motion representation. With 3D space voxelization, the key idea of 3DV is to encode 3D motion information within depth video into a regular voxel set (i.e., 3DV) compactly, via temporal rank pooling. Each available 3DV voxel intrinsically involves 3D spatial and motion feature jointly. 3DV is then abstracted as a point set and input into PointNet++ for 3D action recognition, in the end-to-end learning way. The intuition for transferring 3DV into the point set form is that, PointNet++ is lightweight and effective for deep feature learning towards point set. Since 3DV may lose appearance clue, a multi-stream 3D action recognition manner is also proposed to learn motion and appearance feature jointly. To extract richer temporal order information of actions, we also divide the depth video into temporal splits and encode this procedure in 3DV integrally. The extensive experiments on 4 well-established benchmark datasets demonstrate the superiority of our proposition. Impressively, we acquire the accuracy of 82.4% and 93.5% on NTU RGB+D 120 [13] with the cross-subject and crosssetup test setting respectively. 3DV's code is available at https://github.com/3huo/3DV-Action., Comment: Accepted by CVPR2020

Multi-view clustering is a long-standing important research topic, however, remains challenging when handling high-dimensional data and simultaneously exploring the consistency and complementarity of different views. In this work, we present a novel Reciprocal Multi-layer Subspace Learning (RMSL) algorithm for multi-view clustering, which is composed of two main components: Hierarchical Self-Representative Layers (HSRL), and Backward Encoding Networks (BEN). Specifically, HSRL constructs reciprocal multi-layer subspace representations linked with a latent representation to hierarchically recover the underlying low-dimensional subspaces in which the high-dimensional data lie; BEN explores complex relationships among different views and implicitly enforces the subspaces of all views to be consistent with each other and more separable. The latent representation flexibly encodes complementary information from multiple views and depicts data more comprehensively. Our model can be efficiently optimized by an alternating optimization scheme. Extensive experiments on benchmark datasets show the superiority of RMSL over other state-of-the-art clustering methods.

The industrial robot usually has high repeatability but relatively lower accuracy. Therefore, error compensation plays a pivotal role in many industrial robotic applications with high accuracy requirement. In this paper, we present a novel computational method that utilizes a hybrid model that consists of Local Product-Of-Exponential (POE) and Gaussian Process Regression (GPR) to compensate the positioning errors of the industrial robotic manipulator for high accuracy industrial robotic applications. Specifically in the proposed method, the Local POE calibration method is first applied to calibrate the robot forward kinematic model to reduce the geometric error. Then the GPR is applied to learn the inverse kinematic model to further compensate the residual error in task space. We also demonstrate the robustness and effectiveness of our proposed method by showing the reduction of norm pose error by up to 37.2%, compared to the existing methods with multiple datasets.

Multi-instance multi-label (MIML) learning has many interesting applications in computer visions, including multi-object recognition and automatic image tagging. In these applications, additional information such as bounding-boxes, image captions and descriptions is often available during training phrase, which is referred as privileged information (PI). However, as existing works on learning using PI only consider instance-level PI (privileged instances), they fail to make use of bag-level PI (privileged bags) available in MIML learning. Therefore, in this paper, we propose a two-stream fully convolutional network, named MIML-FCN+, unified by a novel PI loss to solve the problem of MIML learning with privileged bags. Compared to the previous works on PI, the proposed MIML-FCN+ utilizes the readily available privileged bags, instead of hard-to-obtain privileged instances, making the system more general and practical in real world applications. As the proposed PI loss is convex and SGD compatible and the framework itself is a fully convolutional network, MIML-FCN+ can be easily integrated with state of-the-art deep learning networks. Moreover, the flexibility of convolutional layers allows us to exploit structured correlations among instances to facilitate more effective training and testing. Experimental results on three benchmark datasets demonstrate the effectiveness of the proposed MIML-FCN+, outperforming state-of-the-art methods in the application of multi-object recognition., Accepted in CVPR 2017