Abstract The current instance segmentation method can achieve satisfactory results in common scenarios. However, under the overlap or partial occlusion between targets caused by the complex scenes, accurate segmentation of pigs remains a challenging task. To address the problem, the authors propose an instance segmentation method based on Mask Scoring region‐based convolutional neural networks (R‐CNN) (MS R‐CNN), which creates the adversarial network called MaskDis in the head branch of MS R‐CNN. The MaskDis is trained as a discriminator using a generative adversarial network, and the MS R‐CNN model is used as a generator during model training. The adversarial training enables the generator to learn context information and features at the pixel level, which effectively improves the segmentation quality under pigs’ overlapping or dense occlusions scenes. Experimental conducted on the pig object segmentation dataset show that the proposed approach achieves a precision of 92.03%, a recall of 92.18%, and an F1 score of 0.9210. Compared with the basic MS R‐CNN model, the approach achieved a 2.25% improvement in precision and 1.18% improvement in F1 score. Furthermore, the improved approach outperformed advanced instance segmentation methods such as YOLACT, Swin Transformer, YOLOv5‐seg, and SOLOv2 on COCO evaluation metrics. These experimental results demonstrate the effectiveness of the proposed approach in instance segmentation of pigs in complex scenes, providing technical support for non‐contact pig automatic management.

This article proposes a simple yet effective multiobjective evolutionary algorithm (EA) for dealing with problems with irregular Pareto front. The proposed algorithm does not need to deal with the issues of predefining weight vectors and calculating indicators in the search process. It is mainly based on the thought of adaptively selecting multiple promising search directions according to crowdedness information in local objective spaces. Concretely, the proposed algorithm attempts to dynamically delete an individual of poor quality until enough individuals survive into the next generation. In this environmental selection process, the proposed algorithm considers two or three individuals in the most crowded area, which is determined by the local information in objective space, according to a probability selection mechanism, and deletes the worst of them from the current population. Thus, these surviving individuals are representative of promising search directions. The performance of the proposed algorithm is verified and compared with seven state-of-the-art algorithms [including four general multi/many-objective EAs and three algorithms specially designed for dealing with problems with irregular Pareto-optimal front (PF)] on a variety of complicated problems with different numbers of objectives ranging from 2 to 15. Empirical results demonstrate that the proposed algorithm has a strong competitiveness power in terms of both the performance and the algorithm compactness, and it can well deal with different types of problems with irregular PF and problems with different numbers of objectives.

Decomposition approach is an important component in multi-objective evolutionary algorithm based on decomposition (MOEA/D), which is a popular method for handing many-objective optimization problems (MaOPs). This paper presents a theoretical analysis on the convergence ability of using the typical weighted sum (WS), Tchebycheff (TCH) or penalty-based boundary intersection (PBI) approach in a basic MOEA/D for solving two benchmark MaOPs. The results show that using WS, the algorithm can always find an optimal solution for any subproblem in polynomial expected runtime. In contrast, the algorithm needs at least exponential expected runtime for some subproblems if using TCH or PBI. Moreover, our analyses discover an obvious shortcoming of using WS, that is, the optimal solutions of different subproblems are easily corresponding to the same solution. In addition, this analysis indicates that if using PBI, a small value of the penalty parameter is a good choice for faster converging to the Pareto front, but it may lose the diversity. This study reveals some optimization behaviors of using three typical decomposition approaches in the well-known MOEA/D framework for solving MaOPs.

Decomposition-based multiobjective evolutionary algorithms (MOEAs) are a class of popular methods for solving the multiobjective optimization problems (MOPs), and have been widely studied in numerical experiments and successfully applied in practice. However, we know little about these algorithms from the theoretical aspect. In this paper, we present running time analysis of a simple MOEA with mutation and crossover based on the MOEA/D framework (MOEA/D-C) on five pseudo-Boolean functions. Our rigorous theoretical analysis shows that by properly setting the number of subproblems, the upper bounds of expected running time of MOEA/D-C obtaining a set of solutions to cover the Pareto fronts (PFs) of these problems are apparently lower than those of the one with mutation-only (MOEA/D-M). Moreover, to effectively obtain a set of solutions to cover the PFs of these problem, MOEA/D-C only needs to decompose these MOPs into several subproblems with a set of simple weight vectors while MOEA/D-M needs to find Ω(n) optimally decomposed weight vectors. This result suggests that the use of crossover in decomposition-based MOEA can simplify the setting of weight vectors for different problems and make the algorithm more efficient. This paper provides some insights into the working principles of MOEA/D and explains why some existing decomposition-based MOEAs work well in computational experiments.

Somatic contiguous hypermutation (CHM) operators are important variation operators in artificial immune systems. The few existing theoretical studies are only concerned with understanding the optimization behavior of CHM operators on solving single-objective optimization problems. The MOEA/D framework is one of the most popular strategies for solving multi-objective optimization problems (MOPs). In this paper, we present a runtime analysis of using two CHM operators in MOEA/D framework for solving five benchmark MOPs, including four bi-objective and one many-objective problems. Our analyses show that the expected runtimes of CHM operators on the four bi-objective problems are better than or as good as that of the well-studied standard bit mutation operator. Moreover, using CHM operators in MOEA/D framework can improve the best known upper bound on the many-objective problem by a factor of n. This paper provides insight into understanding the optimization behavior of CHM operators in the well-known MOEA/D framework, and indicates that using the CHM operator in MOEA/D framework is a promising method for handling MOPs.

Decomposition-based multiobjective evolutionary algorithms (MOEAs) are a class of popular methods for solving multiobjective optimization problems (MOPs), and have been widely studied in numerical experiments and successfully applied in practice. However, we know little about these algorithms from the theoretical aspect. In this paper, we present a running time analysis of a simple MOEA with crossover based on the MOEA/D framework (MOEA/D-C) on four discrete optimization problems. Our rigorous theoretical analysis shows that the MOEA/D-C can obtain a set of Pareto optimal solutions to cover the Pareto front of these problems in expected running time apparently lower than the one without crossover. Moreover, the MOEA/D-C only needs to decompose an MOP into a few scalar optimization subproblems according to several simple weight vectors. This result suggests that the use of crossover in decomposition-based MOEA can simplify the setting of weight vector for different problems and make the algorithm more efficient. This study theoretically explains why some decomposition-based MOEAs work well in computational experiments and provides insights in design of MOEAs for MOPs in future research.

In this paper, we propose a novel evolutionary algorithm for automatically creating neural network architectures. The proposed algorithm utilizes basic building blocks from existing advanced networks to initialize the population. During the evolutionary process, the algorithm generates new individuals (that is, new networks) which are constructed by making use of different blocks from different networks. Moreover, the encoding scheme, genetic operators and fitness function are well designed. As a result, the generated network architecture, which has a strong heterogeneous property, tends to integrate the merits of existing advanced networks. Experimental results show that the network architecture created by the proposed algorithm can achieve higher classification accuracy than the reference network architectures and the ones evolved by other state-of-the-art evolutionary topology design methods, demonstrating the effectiveness of the proposed algorithm on automatically creating network architectures.