Text

Inferring Latent Domains for Unsupervised Deep Domain Adaptation

Unsupervised Domain Adaptation (UDA) refers to the problem of learning a model in a target domain where labeled data are not available by leveraging information from annotated data in a source domain. Most deep UDA approaches operate in a single-source, single-target scenario, i.e., they assume that the source and the target samples arise from a single distribution. However, in practice most datasets can be regarded as mixtures of multiple domains. In these cases, exploiting traditional single-source, single-target methods for learning classification models may lead to poor results. Furthermore, it is often difficult to provide the domain labels for all data points, i.e. latent domains should be automatically discovered. This paper introduces a novel deep architecture which addresses the problem of UDA by automatically discovering latent domains in visual datasets and exploiting this information to learn robust target classifiers. Specifically, our architecture is based on two main components, i.e. a side branch that automatically computes the assignment of each sample to its latent domain and novel layers that exploit domain membership information to appropriately align the distribution of the CNN internal feature representations to a reference distribution. We evaluate our approach on publicly available benchmarks, showing that it outperforms state-of-the-art domain adaptation methods.

Ketersediaan

Informasi Detail

Judul Seri

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE; Vol.43 No.2 February 2021

No. Panggil

-

Penerbit

: .,

Deskripsi Fisik

p. 485 - 498

Bahasa

English

ISBN/ISSN

-

Klasifikasi

-

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

OBJECT RECOGNITION
UNSUPERVISED DOMAIN ADAPTATION
BATCH NORMALIZATION
DOMAIN DISCOVERY

Info Detail Spesifik

DOI: 10.1109/TPAMI.2019.2933829

Pernyataan Tanggungjawab

Massimiliano Mancini, Lorenzo Porzi, Samuel Rota Bulo, Barbara Caputo, Elisa Ricci

Versi lain/terkait

Lampiran Berkas

Komentar