Ansheng Deng

Group regularization is commonly employed in network pruning to achieve structured model compression. However, the rationale behind existing studies on group regularization predominantly hinges on the sparsity capabilities of $L_{p}$ regularizers. This singular focus may lead to erroneous interpretations. In response to these limitations, this article proposes a novel framework for evaluating the penalization efficacy of group regularization methods by analyzing the impact of $L_{p}$ regularizers on weight magnitudes and weight group magnitudes. Within this framework, we demonstrate that $L_{1,2}$ regularization, contrary to prevailing literature, indeed exhibits favorable performance in structured pruning tasks. Motivated by this insight, we introduce a hybrid group regularization approach that integrates $L_{1,2}$ regularization and group $L_{1/2}$ regularization (denoted as HGL $_{1,2}$ & $L_{1/2}$ ). This novel method addresses the challenge of selecting appropriate $L_{p}$ regularizers for penalizing weight groups by leveraging $L_{1,2}$ regularization for penalizing groups with magnitudes exceeding a critical threshold while employing group $L_{1/2}$ regularization for other groups. Experimental evaluations are conducted to verify the efficiency of the proposed hybrid group regularization method and the viability of the introduced framework.

Image moments, as a kind of global feature descriptor of images, have become a valuable tool for pattern recognition and image analysis. However, traditional methods are mainly used to deal with grayscale images. In this paper, we apply quaternions to fast and accurate polar harmonic Fourier moments, proposing a kind of quaternion fast and accurate polar harmonic Fourier moment (QFAPHFM) capable of handling color images. Furthermore, this paper provides a detailed analysis of the invariance of QFAPHFMs under rotation, scaling, and translation transformations. The experimental results show that QFAPHFMs exhibit excellent performance in both image reconstruction and object recognition tasks. QFAPHFMs achieve accurate image reconstruction under noiseless and noisy conditions, and demonstrate excellent recognition performance in the color-based object recognition tasks. (c) 2024 Optica Publishing Group

In the field of image watermarking, imperceptibility, robustness, and watermarking capacity are key indicators for evaluating the performance of watermarking techniques. However, these three factors are often mutually constrained, posing a challenge in achieving a balance among them. To address this issue, this paper presents a novel image watermark detection algorithm based on local fast and accurate polar harmonic Fourier moments (FAPHFMs) and the BKF–Rayleigh distribution model. Firstly, the original image is chunked without overlapping, the entropy value is calculated, the high-entropy chunks are selected in descending order, and the local FAPHFM magnitudes are calculated. Secondly, the watermarking signals are embedded into the robust local FAPHFM magnitudes by the multiplication function, and then MMLE based on the RSS method is utilized to estimate the statistical parameters of the BKF–Rayleigh distribution model. Finally, a blind image watermarking detector is designed using BKF–Rayleigh distribution and LO decision criteria. In addition, we derive the closed expression of the watermark detector using the BKF–Rayleigh model. The experiments proved that the algorithm in this paper outperforms the existing methods in terms of performance, maintains robustness well under a large watermarking capacity, and has excellent imperceptibility at the same time. The algorithm maintains a well-balanced relationship between robustness, imperceptibility, and watermarking capacity.

Continuous orthogonal moments are widely used in various image techniques due to their simplicity and good rotational invariance and stability. In recent years, numerous excellent continuous orthogonal moments have been developed, among which polar harmonic Fourier moments (PHFMs) exhibit strong image description capabilities. However, the numerical integration error is large in the calculation, which seriously affects the calculation accuracy, especially in higher-order calculation. In this paper, a continuous orthogonal moments-fast and accurate PHFM (FAPHFM) is proposed. It utilizes the polar pixel tiling technique to reduce numerical errors in the computation; this method particularly improves the accuracy of higher-order moments of traditional PHFMs. However, as accuracy increases, calculation complexity also increases. To address this issue, an eight-way symmetric/anti-symmetric calculation of the angular and radial functions was performed using the symmetry and anti-symmetry of traditional PHFMs, and clustering of pixels was performed as a way to improve the computational speed. The experimental results show that FAPHFMs perform better in image reconstruction (including noise), with higher computational accuracy, lower time complexity, and better image description ability.

Collaborative Software Development (CSD) as an effective software development paradigm has achieved rapid development. In CSD, one critical and challenging problem is to find a group of compatible and diverse developers who can complete the assigned task as quickly as possible. To solve this problem, most previous approaches focus on measuring the relevance of tasks and developers based on their historical interactions. However, such approaches usually suffer from data sparsity and cold start problem which may reduce the recommendation accuracy. Moreover, previous approaches often ignored the diversity of team members which may reduce the overall collaboration efficiency. In this paper, we propose an attentive text-enhanced graph embedding learning framework, termed as CsdRec. We first incorporate text embedding into one-hop interaction learning and two-hop graph learning to learn the relevance between tasks and team members. Then, we explicitly model the team members’ diversity and incorporate it with relevance. Finally, to evaluate the performance of CsdRec, we conduct extensive experiments on two real-world datasets. The experimental results show that CsdRec outperforms other state-of-the-art approaches significantly.

Code review as an effective software quality assurance practice has been widely applied in many open-source software communities. However, finding a suitable reviewer for certain codes can be very challenging in open-source communities due to the difficulty of learning the characteristics of reviewers and the code-reviewer interaction sparsity in open-source software communities. To tackle this problem, most previous approaches focus on learning developers’ capabilities and experiences and recommending suitable developers based on their historical interactions. However, such approaches usually suffer from data-sparsity and noise problems, which may reduce the recommendation accuracy. In this paper, we propose an attentive neighbor embedding propagation enhanced code reviewer recommendation framework (termed ANEP). In ANEP, we first construct the reviewer–code interaction graph and learn the semantic representations of the reviewer and code based on the transformer model. Then, we explicitly explore the attentive high-order embedding propagation of reviewers and code and refine the representations along their neighbors. Finally, to evaluate the effectiveness of ANEP, we conduct extensive experiments on four real-world datasets. The experimental results show that ANEP outperforms other state-of-the-art approaches significantly.

Knowledge reduction is a crucial topic in formal concept analysis. There always exists uncertain, symmetric linguistic-evaluation information in social life, which leads to high complexity in the process of knowledge representation. In order to overcome this problem, we are focused on studying the linguistic-concept-reduction methods in an uncertain environment with fuzzy linguistic information. Based on three-way decisions and an attribute-oriented concept lattice, we construct a fuzzy-object-induced three-way attribute-oriented linguistic (FOEAL) concept lattice, which provides complementary conceptual structures of a three-way concept lattice with symmetric linguistic-evaluation information. Through the granular concept of the FOEAL lattice, we present the corresponding linguistic concept granular consistent set and granular reduction. Then, we further employ the linguistic concept discernibility matrix and discernibility function to calculate the granular reduction set. A similar issue on information entropy is investigated to introduce a method of entropy reduction for the FOEAL lattice, and the relation between the linguistic concept granular reduction and entropy reduction is discussed. The efficiency of the proposed method is depicted by some examples and comparative analysis.