Mode collapse remains the primary unresolved challenge within generative adversarial networks (GANs). In this work, we introduce an innovative approach that supplements the discriminator by additionally enforcing the similarity between the generated and real distributions. We implement a one-sample test on the generated samples and employ the resulting test statistic to penalize deviations from the real distribution. Our method encompasses a practical strategy to estimate distributions, compute the test statistic via a differentiable function, and seamlessly incorporate test outcomes into the training objective. Crucially, our approach preserves the convergence and theoretical integrity of GANs, as the introduced constraint represents a requisite condition for optimizing the generator training objective. Notably, our method circumvents reliance on regularization or network modules, enhancing compatibility and facilitating its practical application. Empirical evaluations on diverse public datasets validate the efficacy of our proposed approach.

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.

Deep Convolutional Neural Networks (DCNNs) have achieved impressive performance in Single Image Super-Resolution (SISR). To further improve the performance, existing CNN-based methods generally focus on designing deeper architecture of the network. However, we argue blindly increasing network's depth is not the most sensible way. In this paper, we propose a novel end-to-end Residual Neuron Attention Networks (RNAN) for more efficient and effective SISR. Structurally, our RNAN is a sequential integration of the well-designed Global Context-enhanced Residual Groups (GCRGs), which extracts super-resolved features from coarse to fine. Our GCRG is designed with two novelties. Firstly, the Residual Neuron Attention (RNA) mechanism is proposed in each block of GCRG to reveal the relevance of neurons for better feature representation. Furthermore, the Global Context (GC) block is embedded into RNAN at the end of each GCRG for effectively modeling the global contextual information. Experiments results demonstrate that our RNAN achieves the comparable results with state-of-the-art methods in terms of both quantitative metrics and visual quality, however, with simplified network architecture.

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.

Accurate and robust head pose estimation is a challenging computer vision task. In most existing methods, single-modal RGB or depth images are directly used for head pose estimation. The obvious drawbacks of these methods are two fold: (1) Traditional shallow models are not good at learning representative features. (2) They are single-modal approaches, resulting in sensitivity to noise. As such, in this work we propose a novel multi-modal regression model for head pose estimation, named mixture of deep regression networks (MoDRN). It only uses good examples for one modality to learn sub-network parameters. Thus, the sub-networks tend to be better trained and more robust to noise, making significant improved performance in their combination. Experiments on public datasets such as BIWI and BU-3DFE show the effectiveness of our approach.

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.

Facial age estimation is a challenging problem in computer vision. Existing methods can be classified into two categories: global and person-specific. In practice, the person-specific methods have shown better performance, however it still has some inherit problems such as over learning and mis-assignment of age estimators for unseen facial images. To fix these problems, this paper proposes correlated warped Gaussian processes (CWGP) regression for gender-specific age estimation. It uses two correlated regressors to accurately approximate the gender-specific mapping from facial features to age. Extensive experiments demonstrate the superiority of our method over state-of-the-art methods.

In this paper, a new system for license plate characters recognition is proposed, on the basis of a novel characters recognition algorithm called sliding window search. This system includes license plate location, license plate characters pre-segmentation and characters recognition based on sliding window search. The Gaussian mixture model is used for background modeling and a Bayesian classifier based on the target tracking technology is used to monitor all vehicles within the scene. The brightness difference between the license plate characters and background is considered. Based on the priori information about the characters width, the license plate characters pre-segmentation is easily acquired. Finally, sliding window search is conducted on the license plate characters. Compared with other license plate characters recognition systems, this system has a high recognition accuracy and has good robustness even in a complex environment.

Modern science is increasingly data-driven and collaborative in nature. Comparing to ordinary data processing, big data processing that is mixed with great missing date must be processed rapidly. Considering this requirement this paper proposes a dynamic perception rule acquirement algorithm to implement fast and accurate information decision supporting model for incomplete data. It is inevitable that information contains incomplete data, and huge information being processing require fast algorithm to complete knowledge extraction. The method based on dynamic perception rule can achieve automatic analysis and intelligent cognition for the information decision supporting. Based on direction of maximum entropy at any moment, the perception rule can improve the recognition rate. Furthermore the dynamic perception rule adopts the tolerant relation to accommodate the incomplete data processing capability. The simulative analysis of diesel engine fault shows that the dynamic perception rule can achieve fast information decision supporting and the accuracy is certainly improved even for incomplete data.

Modern science is increasingly data-driven and collaborative in nature. Comparing to ordinary data processing, big data processing that is mixed with great missing date must be processed rapidly. The Rough Set was generated to deal with the large data.In this paper, we proposed animproved algorithm for dynamic Cognitive extractionwhich deals with adaptive fuzzy attribute values and the fuzzy attribute reduction aiming at uncertainty datasuch asdata with diversity or missing character faced by the big data with using Fuzzy Rough Set Theory.At the aspect of information decision, according to the Real-time input information, it deep analyzes the dynamic information entropy of the data itself and chooses the biggest prediction information entropy direction for the cognitive rules to achieve rapid recognitive of data, complete information of quick decision.Because the algorithm is adopted to predict the best direction of information entropy, so the recognitive effect is also improved. At the end of the paper, we have analyzed superiority of the dynamic cognitive algorithm by using breast cancer data as the foundation.

Mixture of regressions is one of the most well-known statistical techniques for the problem of head pose estimation. However, conventional approaches are often sensitive to noise and suffer from underdetermined problem when the training data is insufficient (i.e., the number of training samples for some regressors is less than the dimensionality of the image features). In this paper, we propose a novel approach, named mixture of related regressions (MReR) to address above limitations. By imposing an additional similarity constraint on related regressors, MReR can significantly enhance robustness and avoid uncertainty for head pose estimation. As a nontrivial byproduct, we also develop an EM-type algorithm to efficiently solve the MReR model. Experimental results on both synthetic and real-world datasets demonstrate the benefits of MReR.

Accurate and efficient detection of circular objects in images is a challenging computer vision problem. Existing circular object detection methods can be broadly classified into two categories: voting based and maximum likelihood estimation (MLE) based. The former is robust to noise, however its computational complexity and memory requirement are high. On the other hand, MLE based methods (e.g., robust least squares fitting) are more computationally efficient but sensitive to noise, and can not detect multiple circles. This letter proposes Probabilistic Pairwise Voting (PPV), a fast and robust algorithm for circular object detection based on an extension of Hough Transform. The main contributions are threefold. 1) We formulate the problem of circular object detection as finding the intersection of lines in the three dimensional parameter space (i.e., center and radius of the circle). 2) We propose a probabilistic pairwise voting scheme to robustly discover circular objects under occlusion, image noise and moderate shape deformations. 3) We use a mode-finding algorithm to efficiently find multiple circular objects. We demonstrate the benefits of our approach on two real-world problems: 1) detecting circular objects in natural images, and 2) localizing iris in face images.

A new fingerprint matching algorithm using the elaborate combination of minutiae and curvature maps from fingerprint images is proposed in this paper. First of all, we propose a simple method for curvature calculation based on fingerprint orientation fields from fingerprint images. Secondly, a curvature-based minutia specifier, which appears to be a circular pattern, is introduced by taking sampling steps on curvature map around a minutia serving as a sampling center. Thirdly, a measurement on similarity degree between two minutia specifiers is presented and a reference corresponding minutia pair validation algorithm is also described based on the reliable and maximum curvature points to increase the accuracy of our system. Finally, a fingerprint matching algorithm, based on our proposed minutia specifiers, is developed and tested on a public domain collection of fingerprint images, DB1 set A, FVC2002. The results demonstrate the good performance of our method proposed here.

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.