Instance-level human parsing is aimed at separately partitioning the human body into different semantic parts for each individual, which remains a challenging task due to human appearance/pose variation, occlusion and complex backgrounds. Most state-of-the-art methods follow the “parsing-by-detection” paradigm, which relies on a trained detector to localize persons and then sequentially performs single-person parsing for each person. However, this paradigm is closely related to the detector, and the runtime is proportional to the number of persons in an image. In this paper, we present a novel detection-free framework for instance-level human parsing in an end-to-end manner. We decompose instance-level human parsing into two subtasks via a unified network: 1) semantic segmentation for pixel-level classification as a human part and 2) instance segmentation for mask-level classification as a person. The framework can directly predict the human-part semantic mask for all persons and binary masks for instance-level persons in parallel. The parsing result of each person can be acquired via a Hadamard product between the human-part semantic mask and the corresponding person's binary mask. Extensive experiments demonstrate that our proposed method performs favorably against state-of-the-art methods on the CIHP and MHP v2 datasets.

Accurate tumor segmentation is crucial for esophageal cancer radiotherapy treatment planning. The low contrast among the esophagus, tumors, and surrounding tissues, and irregular tumor shapes limit the performance of automatic segmentation methods. In this paper, we aim to exploit the irregular shapes of tumors to facilitate accurate segmentation. We propose a simple and pluggable shape-aware contrastive deep supervision network (SCDSNet) with shape-aware regularization and voxel-to-voxel contrastive deep supervision. Specifically, the shape-aware regularization with an uncertainty minimization strategy encourages the precise predictions of an additional shape-aware head. The voxel-to-voxel contrastive deep supervision enhances the multi-scale shape-tumor contrast for better voxel-to-voxel prediction of shapes. The proposed method is simple and highly pluggable, which can easily be extended to other frameworks. Further, we establish a large in-house dataset on esophageal cancer to validate the effectiveness of our proposed method. The quantitative and qualitative experimental results demonstrate the effectiveness of SCDSNet on the esophageal cancer dataset.

Dynamic multiobjective optimization problems (DMOPs) challenge multiobjective evolutionary algorithms (MOEAs) because those problems change rapidly over time. The class of DMOPs whose objective functions change over time steps, in ways that exhibit some hidden patterns has gained much attention. Their predictability indicates that the problem exhibits some correlations between solutions obtained in sequential time periods. Most of the current approaches use linear models or similar strategies to describe the correlations between historical solutions obtained, and predict the new solutions in the following time period as an initial population from which the MOEA can begin searching in order to improve its efficiency. However, nonlinear correlations between historical solutions and current solutions are more common in practice, and a linear model may not be suitable for the nonlinear case. In this paper, we present a support vector regression (SVR)-based predictor to generate the initial population for the MOEA in the new environment. The basic idea of this predictor is to map the historical solutions into a high-dimensional feature space via a nonlinear mapping, and to do linear regression in this space. SVR is used to implement this process. We incorporate this predictor into the MOEA based on decomposition (MOEA/D) to construct a novel algorithm for solving the aforementioned class of DMOPs. Comprehensive experiments have shown the effectiveness and competitiveness of our proposed predictor, comparing with the state-of-the-art methods.

This paper introduces a differential prediction model to predict the varying Pareto-Optimal Solutions (POS) when solving dynamic multiobjective optimization problems (DMOPs). In dynamic multiobjective optimization problems, several competing objective functions and/or constraints change over time. As a consequence, the Pareto-Optimal Solutions and/or Pareto-Optimal Front may vary over time. The differential prediction model is used to forecast the shift vector in the decision space of the centroid in the population through the centroid's historical locations in three previous environments. This differential prediction model is incorporated into a multiobjective evolutionary algorithm based on decomposition to solve DMOPs. After detecting the environmental change, half of individuals in the population are forecasted their new positions in the decision space by using the differential prediction model and the others' positions are retained. The proposed model is tested on a number of typical benchmark problems with several dynamic characteristics. Experimental results show that the proposed model is competitively in comparisons with the other state-of-the-art models or approaches that were proposed for solving DMOPs.