arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.05684cs.CV
收藏

快速实时的反事实推理

Fast Real-time Counterfactual Explanations

University of California, Irvine(加州大学尔湾分校)

Yunxia Zhao

摘要:

考虑反事实解释,这是为了回答{ \it为什么预测是A类而不是B类。}与以往基于优化的方法不同,借鉴多域图像到图像翻译算法的发展,提出了一种无需优化的快速实时的【形】反事实解释(FRACE)算法。从starGAN构建,Transformer被训练为残差生成器,该残差生成器以在提案扰动损失下约束的分类器为条件,该提案扰动损失保持查询图像的内容信息,但仅改变类特定的语义信息。Transformer可以将查询图像传输到任何反事实类,并且在推理期间,我们的解释只能在向前的时间内由它生成。该方法速度快,能满足实时的【形】实际应用。由于GAN的对抗训练,我们的解释也比其他同行更真实。实验结果表明,我们的建议是优于现有的最先进的质量和速度方面。

英文摘要:

Counterfactual explanations are considered, which is to answer {\it why the prediction is class A but not B.} Different from previous optimization based methods, an optimization-free Fast ReAl-time Counterfactual Explanation (FRACE) algorithm is proposed benefiting from the development of multi-domain image to image translation algorithms. Built from starGAN, a transformer is trained as a residual generator conditional on a classifier constrained under a proposal perturbation loss which maintains the content information of the query image, but just the class-specific semantic information is changed. The transformer can transfer the query image to any counterfactual class, and during inference, our explanation can be generated by it only within a forward time. It is fast and can satisfy the real-time practical application. Because of the adversarial training of GAN, our explanation is also more realistic compared to other counterparts. The experimental results demonstrate that our proposal is better than the existing state of the art in terms of quality and speed.

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。

↑