Improving Diversity with Adversarially Learned Transformations for Domain Generalization-猫眼课题宝

DOI：

10.1109/wacv56688.2023.00051

发表时间：

2022-06

期刊：

2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Tejas Gokhale;Rushil Anirudh;J. Thiagarajan;B. Kailkhura;Chitta Baral;Yezhou Yang

在单一源领域的概括（SSDG）中，最大化合成域的多样性已成为最有效的SSDG成功策略之一。或者因为转换的特定选择可能无法涵盖域中通常发生的转变类型，以解决此问题，我们提出了一个名为ALT的新型框架：对手学习的转型，使用对手的神经网络来模拟合格的图像转换，但可以通过对分类器进行最初的范围来构建图像变换。分类错误是通过在清洁图像和经验分析的情况下实现其预测的一致性，我们发现这种新形式的对抗性转换可实现多样性的目标，并且可以使所有现有技术在竞争性的基准上均可及其无效。源域的大型转换导致了最新性能：https：//github.com/tejas-gokhale/alt

To be successful in single source domain generalization (SSDG), maximizing diversity of synthesized domains has emerged as one of the most effective strategies. Recent success in SSDG comes from methods that pre-specify diversity inducing image augmentations during training, so that it may lead to better generalization on new domains. However, naïve pre-specified augmentations are not always effective, either because they cannot model large domain shift, or be-cause the specific choice of transforms may not cover the types of shift commonly occurring in domain generalization. To address this issue, we present a novel framework called ALT: adversarially learned transformations, that uses an adversary neural network to model plausible, yet hard image transformations that fool the classifier. ALT learns image transformations by randomly initializing the adversary net-work for each batch and optimizing it for a fixed number of steps to maximize classification error. The classifier is trained by enforcing a consistency between its predictions on the clean and transformed images. With extensive empirical analysis, we find that this new form of adversarial transformations achieves both objectives of diversity and hardness simultaneously, outperforming all existing techniques on competitive benchmarks for SSDG. We also show that ALT can seamlessly work with existing diversity modules to produce highly distinct, and large transformations of the source domain leading to state-of-the-art performance. Code: https://github.com/tejas-gokhale/ALT

Improving Diversity with Adversarially Learned Transformations for Domain Generalization

文献摘要

被引文献

相似文献