论文标题
多任务融合以进行有效的全景局部分段
Multi-task Fusion for Efficient Panoptic-Part Segmentation
论文作者
论文摘要
在本文中，我们介绍了一个新颖的网络，该网络使用共享的编码器生成语义，实例和部分分割，并有效地融合了它们以实现全景零件分割。统一这三个分割问题可以相互改善和一致的表示学习。为了有效地融合所有三个头部的预测，我们引入了一个无参数的关节融合模块，该模块可以动态平衡逻辑并融合它们以创建全景零件分割。我们的方法在城市景观圆形零件（CPP）和帕斯卡圆形零件（PPP）数据集上进行了评估。对于CPP而言，我们提出的联合融合的拟议模型的partPQ分别超过了所有区域和零件细分市场的先前最新点和4.7个百分点。在PPP上，我们的联合融合使用以前的自上而下的合并策略在PARTPQ中的分为3.3个百分点，而PARTPQ中的10.5个百分点则优于模型。
In this paper, we introduce a novel network that generates semantic, instance, and part segmentation using a shared encoder and effectively fuses them to achieve panoptic-part segmentation. Unifying these three segmentation problems allows for mutually improved and consistent representation learning. To fuse the predictions of all three heads efficiently, we introduce a parameter-free joint fusion module that dynamically balances the logits and fuses them to create panoptic-part segmentation. Our method is evaluated on the Cityscapes Panoptic Parts (CPP) and Pascal Panoptic Parts (PPP) datasets. For CPP, the PartPQ of our proposed model with joint fusion surpasses the previous state-of-the-art by 1.6 and 4.7 percentage points for all areas and segments with parts, respectively. On PPP, our joint fusion outperforms a model using the previous top-down merging strategy by 3.3 percentage points in PartPQ and 10.5 percentage points in PartPQ for partitionable classes.
