用循环损失提升跨域生成模型的翻译精度
Cross Domain Adaptation using Adversarial networks with Cyclic loss
- 引入循环一致性损失约束生成器，增强源域到目标域的翻译能力
- 在多个数据集上验证了生成图像的保真度和域适应效果显著提升
- 适合需要无监督跨域数据生成的研究者使用
深度学习方法对训练数据的领域分布高度敏感，微小偏离即导致预测精度显著下降。本文研究了一类提升对抗设置下生成网络跨域翻译性能的技术，重点考察了激活函数、编码器-解码器架构，并提出一种称为循环损失的新损失函数，以约束生成器学习有效的源域到目标域映射。该问题源于众多应用场景，例如在无监督条件下从合成输入生成标注数据，或将此类翻译网络与原始领域网络结合，实现深度学习模型在不同领域的泛化。
原文摘要 · Abstract (English)
Deep Learning methods are highly local and sensitive to the domain of data they are trained with. Even a slight deviation from the domain distribution affects prediction accuracy of deep networks significantly. In this work, we have investigated a set of techniques aimed at increasing accuracy of generator networks which perform translation from one domain to the other in an adversarial setting. In particular, we experimented with activations, the encoder-decoder network architectures, and introduced a Loss called cyclic loss to constrain the Generator network so that it learns effective source-target translation. This machine learning problem is motivated by myriad applications that can be derived from domain adaptation networks like generating labeled data from synthetic inputs in an unsupervised fashion, and using these translation network in conjunction with the original domain network to generalize deep learning networks across domains.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。