相似度约束的交互式分割网络  

Interactive Segmentation Network with Similarity Constraints

作　　者：付杰 宣士斌[1,2] 江进宝 FU Jie;XUAN Shi-Bin;JIANG Jin-Bao(School of Artificial Intelligence,Guangxi Minzu University,Nanning 530006,China;Guangxi Key Laboratory of Hybrid Computation and IC Design Analysis,Nanning 530006,China)

机构地区：[1]广西民族大学人工智能学院,南宁530006 [2]广西混杂计算与集成电路设计分析重点实验室,南宁530006

出　　处：《计算机系统应用》2023年第12期233-242,共10页Computer Systems & Applications

基　　金：国家自然科学基金(61866003);广西民族大学研究生教育创新计划(gxun-chxs2021063)。

摘　　要：交互式图像分割是像素级注释和图像编辑的重要工具.现存方法大多采取两阶段预测,首先预测一个粗糙的结果,在第2个阶段细化之前预测的结果来得到更精确的预测,为了使在硬件资源受限时,网络模型仍可以使用,基于此,在两阶段共享同一个网络,为了更好地将标记信息传播到未标记区域,设计了一个相似度约束传播模块,在训练时使用了一个简单的原型提取模块来使正点击向量高度内聚,加速网络收敛,在推理时移除.在推理阶段通过使用意图感知模块来捕获细节,使得预测性能进一步提升.大量实验表明,该方法在所有流行的基准测试上与最先进的方法最有可比性,证明了其有效性.Interactive image segmentation is an important tool for pixel-level annotation and image editing.Most existing methods adopt two-stage prediction:first predicting a rough result,and then refining the previously predicted results in the second stage to obtain more accurate predictions.To ensure the viability of the network model under limited hardware resources,the same network is shared across the two stages.To better propagate labeled information to unlabeled areas,a similarity constraint propagation module is designed.Meanwhile,a simple prototype extraction module is used during training to make forward click vectors highly cohesive,accelerate network convergence,and remove them during inference.At the inference stage,the implementation of intention perception modules to capture details further improves prediction performance.Numerous experiments show that the method is most comparable to the most advanced methods on all popular benchmark tests,demonstrating its effectiveness.

关 键 词：交互式分割 图像分割 语义分割 图网络 深度学习 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]