Variational Adversarial Defense: A Bayes Perspective for Adversarial Training.

Various methods have been proposed to defend against adversarial attacks. However, there is a lack of enough theoretical guarantee of the performance, thus leading to two problems: First, deficiency of necessary adversarial training samples might attenuate the normal gradient's back-propagation, which leads to overfitting and gradient masking potentially. Second, point-wise adversarial sampling offers an insufficient support region for adversarial data and thus cannot form a robust decision-boundary. To solve these issues, we provide a theoretical analysis to reveal the relationship between robust accuracy and the complexity of the training set in adversarial training. As a result, we propose a novel training scheme called Variational Adversarial Defense. Based on the distribution of adversarial samples, this novel construction upgrades the defend scheme from local point-wise to distribution-wise, yielding an enlarged support region for safeguarding robust training, thus possessing a higher promising to defense attacks. The proposed method features the following advantages: 1) Instead of seeking adversarial examples point-by-point (in a sequential way), we draw diverse adversarial examples from the inferred distribution; and 2) Augmenting the training set by a larger support region consolidates the smoothness of the decision boundary. Finally, the proposed method is analyzed via the Taylor expansion technique, which casts our solution with natural interpretability.

Learning by Restoring Broken 3D Geometry.

The key point for an experienced craftsman to repair broken objects effectively is that he must know about them deeply. Similarly, we believe that a model can capture rich geometry information from a shape/scene and generate discriminative representations if it is able to find distorted parts of shapes/scenes and restore them. Inspired by this observation, we propose a novel self-supervised 3D learning paradigm named learning by restoring broken shapes/scenes (collectively called 3D geometry). We first develop a destroy-method cluster, from which we sample methods to break some local parts of an object. Then the destroyed object and the normal object are both sent into a point cloud network to get representations, which are employed to segment points that belong to distorted parts and further reconstruct/restore them to normal. To perform better in these two associated pretext tasks, the model is constrained to capture useful object features, such as rich geometric and contextual information. The object representations learned by this self-supervised paradigm transfer well to different datasets and perform well on downstream classification, segmentation and detection tasks. Experimental results on shape datasets and scene datasets demonstrate that our method achieves state-of-the-art performance among unsupervised methods. We also show experimentally that pre-training with our framework significantly boosts the performance of supervised models.

Limb Pose Aware Networks for Monocular 3D Pose Estimation.

In the task of monocular 3D pose estimation, the estimation errors of limb joints (i.e., wrist, ankle, etc) with a higher degree of freedom(DOF) are larger than that of others (i.e., hip, thorax, etc). Specifically, errors may accumulate along the physiological structure of human body parts, and trajectories of joints with higher DOF bring in higher complexity. To address this problem, we propose a limb pose aware framework, involving a kinematic constraint aware network as well as a trajectory aware temporal module, to improve the 3D prediction accuracy of limb joint positions. Two kinematic constraints named relative bone angles and absolute bone angles are introduced in this paper, the former being used for building the angular relation between adjacent bones and the latter for building the angular relation between bones and the camera plane. As a joint result of two constraints, our work suppresses errors accumulated along limbs. Furthermore, we propose a trajectory-aware network, named as Hierarchical Transformer, which takes temporal trajectories of joints as input and generates fused trajectory estimation as a result. The Hierarchical Transformer consists of Transformer Encoder blocks and aims at improving the performance of fusing temporal features. Under the effect of kinematic constraints and trajectory network, we alleviate the problem of errors accumulated along limbs and achieve promising results. Most of the off-the-shelf 2D pose estimators can be easily integrated into our framework. We perform extensive experiments on public datasets and validate the effectiveness of the framework. The ablation studies show the strength of each individual sub-module.

Association between in vitro fertilization outcomes and inherited thrombophilias: a meta-analysis.

PURPOSE: The aim of this study was to determine whether in vitro fertilization (IVF) outcomes are associated with inherited thrombophilias. METHODS: Several databases including PubMed, Embase, and Cochrane Library were retrieved up to 12 January 2016. The quality of the included studies was assessed by two authors. The associations of the following mutations in inherited thrombophilias and IVF outcomes were explored: factor V Leiden (FVL), prothrombin gene G20210A mutation (PGM), 5,10-methylentetrahydrofolate reductase (MTHFR) C677T, MTHFR (A1298C) and activated protein C resistance (APCR). The main outcome measures included CPR and implantation rate (IR). The relative risk (RR) and its 95 % confidence interval (CI) were calculated for effect index. Heterogeneity test was evaluated by Chi-square based on Q statistic and I (2) statistics. RESULTS: A total of seven articles published between 2007 and 2015 with the ages of subjects between 30.9 and 36.2 were included. For subgroups analysis of CPR or IR, there were no significant differences in MTHFR (C377T), MTHFR (A1298C), FVL, PGM, and FVL/PGM mutation were found between the mutation group and control group (P > 0. 05). CONCLUSIONS: IVF outcomes are not associated with FVL, PGM, MTHFR (C677T), MTHFR (A1298C), and APCR mutation in inherited thrombophilias.