Text

Divergence-Agnostic Unsupervised Domain Adaptation by Adversarial Attacks

Conventional machine learning algorithms suffer the problem that the model trained on existing data fails to generalize well to the data sampled from other distributions. To tackle this issue, unsupervised domain adaptation (UDA) transfers the knowledge learned from a well-labeled source domain to a different but related target domain where labeled data is unavailable. The majority of existing UDA methods assume that data from the source domain and the target domain are available and complete during training. Thus, the divergence between the two domains can be formulated and minimized. In this paper, we consider a more practical yet challenging UDA setting where either the source domain data or the target domain data are unknown. Conventional UDA methods would fail this setting since the domain divergence is agnostic due to the absence of the source data or the target data. Technically, we investigate UDA from a novel view—adversarial attack—and tackle the divergence-agnostic adaptive learning problem in a unified framework. Specifically, we first report the motivation of our approach by investigating the inherent relationship between UDA and adversarial attacks. Then we elaborately design adversarial examples to attack the training model and harness these adversarial examples. We argue that the generalization ability of the model would be significantly improved if it can defend against our attack, so as to improve the performance on the target domain. Theoretically, we analyze the generalization bound for our method based on domain adaptation theories. Extensive experimental results on multiple UDA benchmarks under conventional, source-absent and target-absent UDA settings verify that our method is able to achieve a favorable performance compared with previous ones. Notably, this work extends the scope of both domain adaptation and adversarial attack, and expected to inspire more ideas in the community.

Ketersediaan

Informasi Detail

Judul Seri

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE; Vol.44 No.11 Part 2 November 2022

No. Panggil

-

Penerbit

: .,

Deskripsi Fisik

p. 8196-8211

Bahasa

English

ISBN/ISSN

-

Klasifikasi

NONE

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

TRANSFER LEARNING
MODEL ADAPTATION
DOMAIN GENERALIZATION
UNSUPERVISED DOMAIN ADAPTATION
ADVERSARIAL ATTACKS

Info Detail Spesifik

DOI: 10.1109/TPAMI.2021.3109287

Pernyataan Tanggungjawab

Jingjing Li, Zhekai Du, Lei Zhu, Zhengming Ding, Ke Lu, Heng Tao Shen

Versi lain/terkait

Lampiran Berkas

Komentar