arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.06360cs.CV
收藏

反事实生成式零样本语义分割

Conterfactual Generative Zero-Shot Semantic Segmentation

Jilin University(吉林大学);Singapore University of Technology and Design(新加坡科技设计大学);Boston University(波士顿大学)

Feihong Shen, Jun Liu, Ping Hu

AI总结:

针对零样本语义分割生成模型因虚假统计关系导致预测偏差的问题,提出基于反事实因果推断消除混淆因子的新框架,并设计基于GCN的简单结构,在Pascal-VOC和Pascal-Context数据集上超越基线模型。

摘要:

零样本学习是计算机视觉的重要组成部分。作为经典的下游任务,零样本语义分割因其应用价值而受到研究。一种流行的零样本语义分割方法基于生成模型,多数新提出的工作在同一架构上添加结构来增强该模型。然而,从因果推断的角度看,原始模型的结果受到了虚假统计关系的影响,导致预测表现出严重偏差。在本研究中,我们考虑使用反事实方法来避免原始模型中的混淆因子。基于此方法,我们提出了一种新的零样本语义分割框架。我们的模型在两个真实世界数据集Pascal-VOC和Pascal-Context上与基线模型进行了比较。实验结果表明,所提模型能够超越先前受混淆的模型,并且仍能利用附加结构来提升性能。此外,我们还在本研究中设计了一种基于图卷积网络(GCN)的简单结构。

英文摘要:

zero-shot learning is an essential part of computer vision. As a classical downstream task, zero-shot semantic segmentation has been studied because of its applicant value. One of the popular zero-shot semantic segmentation methods is based on the generative model Most new proposed works added structures on the same architecture to enhance this model. However, we found that, from the view of causal inference, the result of the original model has been influenced by spurious statistical relationships. Thus the performance of the prediction shows severe bias. In this work, we consider counterfactual methods to avoid the confounder in the original model. Based on this method, we proposed a new framework for zero-shot semantic segmentation. Our model is compared with baseline models on two real-world datasets, Pascal-VOC and Pascal-Context. The experiment results show proposed models can surpass previous confounded models and can still make use of additional structures to improve the performance. We also design a simple structure based on Graph Convolutional Networks (GCN) in this work.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑