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 2109.02693cs.CV
收藏

通过域对齐层提高领域自适应网络的可移植性

Improving Transferability of Domain Adaptation Networks Through Domain Alignment Layers

Instituto de Ciência e Tecnologia, Universidade Federal de São(圣保罗联邦大学科学与技术研究所)

Lucas Fernando Alvarenga e Silva, Daniel Carlos Guimarães Pedronette, Fábio Augusto Faria, João Paulo Papa, Jurandy Almeida

摘要:

深度学习(DL)已经成为各种计算机视觉任务中使用的主要方法,因为它在许多任务上取得了相关的结果。然而,在部分或没有标记数据的真实世界场景中,DL方法也容易出现众所周知的域偏移问题。多源无监督领域自适应(MSDA)的目标是通过从一组源模型中分配弱知识来学习未标记领域的预测器。然而,大多数作品进行领域自适应只利用提取的功能,并减少其域转移的损失函数设计的角度来看。在本文中,我们认为,这是不够的,仅根据域级别的功能来处理域移位,但它也是必不可少的,以调整这些信息的特征空间。与以前的作品不同,我们专注于网络设计,并建议在预测器的不同级别嵌入多源版本的DomaIn对齐层(MS-DIAL)。这些层被设计为匹配不同域之间的特征分布,并且可以很容易地应用于各种MSDA方法。为了显示我们的方法的鲁棒性,我们进行了广泛的实验评估,考虑两个具有挑战性的情况:数字识别和对象分类。实验结果表明,我们的方法可以改善最先进的MSDA方法,产生高达+30.64%的相对收益,其分类精度。

英文摘要:

Deep learning (DL) has been the primary approach used in various computer vision tasks due to its relevant results achieved on many tasks. However, on real-world scenarios with partially or no labeled data, DL methods are also prone to the well-known domain shift problem. Multi-source unsupervised domain adaptation (MSDA) aims at learning a predictor for an unlabeled domain by assigning weak knowledge from a bag of source models. However, most works conduct domain adaptation leveraging only the extracted features and reducing their domain shift from the perspective of loss function designs. In this paper, we argue that it is not sufficient to handle domain shift only based on domain-level features, but it is also essential to align such information on the feature space. Unlike previous works, we focus on the network design and propose to embed Multi-Source version of DomaIn Alignment Layers (MS-DIAL) at different levels of the predictor. These layers are designed to match the feature distributions between different domains and can be easily applied to various MSDA methods. To show the robustness of our approach, we conducted an extensive experimental evaluation considering two challenging scenarios: digit recognition and object classification. The experimental results indicated that our approach can improve state-of-the-art MSDA methods, yielding relative gains of up to +30.64% on their classification accuracies.

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。

↑