Inductive Unsupervised Domain Adaptation for Few-Shot Classification via Clustering release_duwegr3z45ennfb3j6zk5zwdji

by Xin Cong, Bowen Yu, Tingwen Liu, Shiyao Cui, Hengzhu Tang, Bin Wang

Released as a article .

2020  

Abstract

Few-shot classification tends to struggle when it needs to adapt to diverse domains. Due to the non-overlapping label space between domains, the performance of conventional domain adaptation is limited. Previous work tackles the problem in a transductive manner, by assuming access to the full set of test data, which is too restrictive for many real-world applications. In this paper, we set out to tackle this issue by introducing a inductive framework, DaFeC, to improve Domain adaptation performance for Few-shot classification via Clustering. We first build a representation extractor to derive features for unlabeled data from the target domain (no test data is necessary) and then group them with a cluster miner. The generated pseudo-labeled data and the labeled source-domain data are used as supervision to update the parameters of the few-shot classifier. In order to derive high-quality pseudo labels, we propose a Clustering Promotion Mechanism, to learn better features for the target domain via Similarity Entropy Minimization and Adversarial Distribution Alignment, which are combined with a Cosine Annealing Strategy. Experiments are performed on the FewRel 2.0 dataset. Our approach outperforms previous work with absolute gains (in classification accuracy) of 4.95%, 9.55%, 3.99% and 11.62%, respectively, under four few-shot settings.
In text/plain format

Archived Files and Locations

application/pdf  469.2 kB
file_iksaqyxhlvclhezcaruinxlnei
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2020-06-23
Version   v1
Language   en ?
arXiv  2006.12816v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 3843ecbd-22c0-4815-83f8-d69c42e2ab4d
API URL: JSON