论文标题
靠近实时语义细分的lookahead对抗学习
Lookahead Adversarial Learning for Near Real-Time Semantic Segmentation
论文作者
论文摘要
语义细分是计算机视觉中最根本的问题之一，对各种应用程序有重大影响。对抗性学习被证明是通过执行高级像素相关性和结构信息来改善语义分割质量的有效方法。但是，最新的语义细分模型不能轻易插入对抗设置中，因为它们并非旨在适应对抗网络中的收敛性和稳定性问题。我们通过建立一个有条件的对抗网络来弥合这一差距，该网络的核心是最先进的分割模型（DEEPLABV3+）。为了解决稳定问题，我们使用嵌入式标签图聚合模块引入了一种新颖的LookAhead对抗学习（负载）方法。我们专注于语义分割模型，这些模型在推断近实时现场应用程序时快速运行。通过广泛的实验，我们证明了所提出的解决方案可以减轻对抗性语义分割设置中的分歧问题，并在三个标准数据集的基线上在基线上进行大量性能改进（+5％）。
Semantic segmentation is one of the most fundamental problems in computer vision with significant impact on a wide variety of applications. Adversarial learning is shown to be an effective approach for improving semantic segmentation quality by enforcing higher-level pixel correlations and structural information. However, state-of-the-art semantic segmentation models cannot be easily plugged into an adversarial setting because they are not designed to accommodate convergence and stability issues in adversarial networks. We bridge this gap by building a conditional adversarial network with a state-of-the-art segmentation model (DeepLabv3+) at its core. To battle the stability issues, we introduce a novel lookahead adversarial learning (LoAd) approach with an embedded label map aggregation module. We focus on semantic segmentation models that run fast at inference for near real-time field applications. Through extensive experimentation, we demonstrate that the proposed solution can alleviate divergence issues in an adversarial semantic segmentation setting and results in considerable performance improvements (+5% in some classes) on the baseline for three standard datasets.
