Mode collapse is a significant unsolved issue of generative adversarial networks (GANs). In this work, we examine the causes of mode collapse from a novel perspective. Due to the nonuniform sampling in the training process, some subdistributions may be missed when sampling data. As a result, even when the generated distribution differs from the real one, the GAN objective can still achieve the minimum. To address the issue, we propose a global distribution fitting (GDF) method with a penalty term to confine the generated data distribution. When the generated distribution differs from the real one, GDF will make the objective harder to reach the minimal value, while the original global minimum is not changed. To deal with the circumstance when the overall real data is unreachable, we also propose a local distribution fitting (LDF) method. Experiments on several benchmarks demonstrate the effectiveness and competitive performance of GDF and LDF.

Abstract Principal component analysis (PCA) is widely used in computer vision for object detection. In this article, we take advantage of the algorithms of PCA and kernel principal component analysis (KPCA) to construct a deep learning model named parallel KPCA‐PCA network (PK‐PCANet). In the proposed model, both of the given PCA and KPCA algorithm are aiming to calculate the filters that will be used in the following convolution layers. The extracted features from PCANet and KPCANet are fused by the strategy of parallel feature fusion. With the aim of reducing the dimensionality of the learned features, the algorithm of compressed sensing is incorporated in the proposed network. According to the cooperative advantages of deep learning network and compressed sensing, the proposed PK‐PCANet model obtains some improvements in several visual recognition tasks. Extensively experiments are performed on face recognition, hand‐written digit recognition and object classification, and the experimental results on various image classification benchmarks such as Extended Yale B, AR, MNIST, CIFAR‐10, and VOC 2007 validated the efficiency of the proposed method of PK‐PCANet.

3D face reconstruction from a single image is an important task in many multimedia applications. Recent works typically learn a CNN-based 3D face model that regresses coefficients of a 3D Morphable Model (3DMM) from 2D images to perform 3D face reconstruction. However, the shortage of training data with 3D annotations considerably limits performance of these methods. To alleviate this issue, we propose a novel 2D-Assisted Learning (2DAL) method that can effectively use “in the wild” 2D face images with noisy landmark information to substantially improve 3D face model learning. Specifically, taking the sparse 2D facial landmark heatmaps as additional information, 2DAL introduces four novel self-supervision schemes that view the 2D landmark and 3D landmark prediction as a self-mapping process, including the landmark self-prediction consistency for 2D and 3D faces respectively, cycle-consistency over the 2D landmark prediction and self-critic over the predicted 3DMM coefficients based on landmark prediction. Using these four self-supervision schemes, 2DAL significantly relieves the demands for the the conventional paired 2D-to-3D annotations and gives much higher-quality 3D face models without requiring any additional 3D annotations. Experiments on AFLW2000-3D, AFLW-LFPA and Florence benchmarks show that our method outperforms state-of-the-arts for both 3D face reconstruction and dense face alignment by a large margin.

Face anti-spoofing aims to detect presentation attack to face recognition--based authentication systems. It has drawn growing attention due to the high security demand. The widely adopted CNN-based methods usually well recognize the spoofing faces when training and testing spoofing samples display similar patterns, but their performance would drop drastically on testing spoofing faces of novel patterns or unseen scenes, leading to poor generalization performance. Furthermore, almost all current methods treat face anti-spoofing as a prior step to face recognition, which prolongs the response time and makes face authentication inefficient. In this article, we try to boost the generalizability and applicability of face anti-spoofing methods by designing a new generalizable face authentication CNN (GFA-CNN) model with three novelties. First, GFA-CNN introduces a simple yet effective total pairwise confusion loss for CNN training that properly balances contributions of all spoofing patterns for recognizing the spoofing faces. Second, it incorporate a fast domain adaptation component to alleviate negative effects brought by domain variation. Third, it deploys filter diversification learning to make the learned representations more adaptable to new scenes. In addition, the proposed GFA-CNN works in a multi-task manner—it performs face anti-spoofing and face recognition simultaneously. Experimental results on five popular face anti-spoofing and face recognition benchmarks show that GFA-CNN outperforms previous face anti-spoofing methods on cross-test protocols significantly and also well preserves the identity information of input face images.

Due to its importance, figure/ground segmentation in video has gained interest recently. The key factor of the segmentation is the construction of the spatio-temporal coherence. Previous works usually use the motion approximation as a measurement of the coherence, resulting in a low accuracy. In this paper, we present a novel method to measure the coherence, and an algorithm for target segmentation and tracking is proposed. Each image is abstracted by some compact and perceptually homogeneous elements, and by representing the elements as sparse linear combinations of dictionary templates, this algorithm capitalizes on the inherent low-rank structure of representations that are learned jointly. The coefficients of the constrained representation will act as the measurement of the spatio-temporal coherence. At last, a simple energy minimization solution with an online parameter-updating scheme is adopted in segmented stage, leading to a binary object's segmentation. Meanwhile, an adaptive dictionary is proposed to enhance the system's robust against occlusion. Our approach outperforms the state-of-the-art methods in object segmentation accuracy.

Template tracking has been extensively investigated in computer vision to track objects for various applications. Tracking based on gradient descent algorithm using image gradient is one of the most popular object tracking method. However, it is difficult to define the relationship between the observed data set and the warping function due to the unobserved heterogeneity of the data set which inevitably results in poor tracking performance. This study proposes a novel method based on hierarchical mixture of expert to perform robust, real‐time tracking from stationary cameras. By extending the idea of hyperplane approximation, the proposed approach establishes a hierarchical mixture of generalised linear regression model instead of a single model which reduces the non‐linear error. The experiments’ results show significant improvement over the traditional hyperplane approximation (HA) approach.

Iris localization is an especially important step in the whole iris recognition system, for it determines the accuracy of matching partially. To improve its accuracy and efficiency, we propose a new iris localization algorithm in this paper, which detects the edge points of iris at some appropriate resolutions and fits circles to these edge points. The experiment results show that the proposed algorithm maintains a good compromise between accuracy and efficiency. The most important merit of this algorithm is that it¿s seldom disturbed by lash occlusion problem.