arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.03455cs.CVcs.LG
收藏

用于领域自适应的硬类纠正

Hard Class Rectification for Domain Adaptation

Xiamen University(厦门大学);Carnegie Mellon University(卡内基梅隆大学)

Yunlong Zhang, Changxing Jing, Huangxing Lin, Chaoqi Chen, Yue Huang, Xinghao Ding, Yang Zou

摘要:

领域自适应(DA)的目的是将知识从标签丰富的相关领域(源领域)转移到标签稀缺的领域(目标领域)。近年来,伪标记在DA中得到了广泛的研究和应用,但这一领域的研究仍然局限于伪标记的不准确性。在本文中,我们揭示了一个有趣的观察,目标样本属于具有较大的域移动类更容易被误分类相比,其他类。这些类被称为硬类,这恶化了DA的性能,限制了DA的应用。我们提出了一种新的框架,称为硬类纠正伪标记(HCRPL),从两个方面来缓解硬类问题。首先,由于难以将目标样本识别为硬类,我们提出了一种简单而有效的方案,称为自适应预测校准(APC),根据每个类的难度来校准目标样本的预测。其次,我们进一步认为,属于硬类的目标样本的预测是容易受到扰动。为了防止这些样本容易被误分类,我们引入时间集成(TE)和自集成(SE)来获得一致的预测。该方法在无监督领域自适应(UDA)和半监督领域自适应(SSDA)中进行了评估。在ImageCLEF、Office-31和WEB-Home等跨领域测试平台上的实验结果验证了该方法的优越性。

英文摘要:

Domain adaptation (DA) aims to transfer knowledge from a label-rich and related domain (source domain) to a label-scare domain (target domain). Pseudo-labeling has recently been widely explored and used in DA. However, this line of research is still confined to the inaccuracy of pseudo-labels. In this paper, we reveal an interesting observation that the target samples belonging to the classes with larger domain shift are easier to be misclassified compared with the other classes. These classes are called hard class, which deteriorates the performance of DA and restricts the applications of DA. We propose a novel framework, called Hard Class Rectification Pseudo-labeling (HCRPL), to alleviate the hard class problem from two aspects. First, as is difficult to identify the target samples as hard class, we propose a simple yet effective scheme, named Adaptive Prediction Calibration (APC), to calibrate the predictions of the target samples according to the difficulty degree for each class. Second, we further consider that the predictions of target samples belonging to the hard class are vulnerable to perturbations. To prevent these samples to be misclassified easily, we introduce Temporal-Ensembling (TE) and Self-Ensembling (SE) to obtain consistent predictions. The proposed method is evaluated in both unsupervised domain adaptation (UDA) and semi-supervised domain adaptation (SSDA). The experimental results on several real-world cross-domain benchmarks, including ImageCLEF, Office-31 and Office-Home, substantiates the superiority of the proposed method.

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。

↑