arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.00236cs.CV
收藏

目标检测中的不确定性感知无监督领域自适应

Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection

Nanyang Technological University(南洋理工大学);Zhejiang University(浙江大学)

Dayan Guan, Jiaxing Huang, Aoran Xiao, Shijian Lu, Yanpeng Cao

摘要:

无监督域自适应目标检测的目的是使检测器从标记的源域适应到未标记的目标域。大多数现有的作品采取两阶段策略,首先生成区域建议,然后检测感兴趣的对象,其中广泛采用对抗性学习来减轻这两个阶段中的域间差异。然而,对抗性学习可能会损害对齐样本的对齐,因为它只是对齐跨域的全局分布。为了解决这个问题,我们设计了一个不确定性感知的领域自适应网络(UaDAN),它引入了条件对抗学习,以不同的方式分别对齐对齐良好和对齐不良的样本。具体来说,我们设计了一个不确定性度量,用于评估每个样本的对齐情况,并自适应地调整对齐良好和对齐不良样本的对抗学习强度。此外,我们利用不确定性度量来实现课程学习,首先执行更容易的图像级对齐,然后逐步进行更困难的实例级对齐。在四个具有挑战性的领域自适应目标检测数据集上的广泛实验表明,UaDAN与最先进的方法相比,具有更好的性能。

英文摘要:

Unsupervised domain adaptive object detection aims to adapt detectors from a labelled source domain to an unlabelled target domain. Most existing works take a two-stage strategy that first generates region proposals and then detects objects of interest, where adversarial learning is widely adopted to mitigate the inter-domain discrepancy in both stages. However, adversarial learning may impair the alignment of well-aligned samples as it merely aligns the global distributions across domains. To address this issue, we design an uncertainty-aware domain adaptation network (UaDAN) that introduces conditional adversarial learning to align well-aligned and poorly-aligned samples separately in different manners. Specifically, we design an uncertainty metric that assesses the alignment of each sample and adjusts the strength of adversarial learning for well-aligned and poorly-aligned samples adaptively. In addition, we exploit the uncertainty metric to achieve curriculum learning that first performs easier image-level alignment and then more difficult instance-level alignment progressively. Extensive experiments over four challenging domain adaptive object detection datasets show that UaDAN achieves superior performance as compared with state-of-the-art methods.

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。

↑