paper-with-me

홈 › Papers

Reducing Distributional Uncertainty by Mutual Information Maximisation and Transferable Feature Learning

2020-08-01 · ECCV 2020 8 · Jian Gao, Yang Hua, Guosheng Hu, Chi Wang, Neil M. Robertson

Distributional uncertainty exists broadly in many real-world applications, one of which in the form of domain discrepancy. Yet in the existing literature, the mathematical definition of it is missing. In this paper, we propose to formulate the distributional uncertainty both between the source(s) and target domain(s) and within each domain using mutual information. Further, to reduce distributional uncertainty (e.g. domain discrepancy), we (1) maximise the mutual information between source and target domains and (2) propose a transferable feature learning scheme, balancing two complementary and discriminative feature learning processes (general texture learning and self-supervised transferable shape learning) according to the uncertainty. We conduct extensive experiments on both domain adaption and domain generalisation using challenging common benchmarks: Office-Home and DomainNet. Results show the great effectiveness of the proposed method and its superiority over the state-of-the-art methods.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptation

Similar Papers 제목 키워드 기반

A review over the applicability of image entropy in analyses of remote sensing datasets

2014-02-05 · S. K. Katiyar, P. V. Arun

Entropy is the measure of uncertainty in any data and is adopted for maximisation of mutual information in many remote sensing operations. The availability of wide entropy variations motivated us for an investigation ove…

Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning

2015-09-29 · NeurIPS 2015 12 · Shakir Mohamed, Danilo Jimenez Rezende

The mutual information is a core statistical quantity that has applications in all areas of machine learning, whether this is in training of density models over multiple data modalities, in maximising the efficiency of n…

BIG-bench Machine Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1

A Comparative Analysis on the Applicability of Entropy in remote sensing

2013-03-27 · Dr. S. K. Katiyar, Arun P. V.

Entropy is the measure of uncertainty in any data and is adopted for maximisation of mutual information in many remote sensing operations. The availability of wide entropy variations motivated us for an investigation ove…

Clustering

Distributionally robust portfolio maximisation and marginal utility pricing in one period financial markets

2021-05-03 · Jan Obloj, Johannes Wiesel

We consider the optimal investment and marginal utility pricing problem of a risk averse agent and quantify their exposure to a small amount of model uncertainty. Specifically, we compute explicitly the first-order sensi…

Improving Sentence Representations with Consensus Maximisation

2018-10-02 · ICLR 2019 5 · Shuai Tang, Virginia R. de Sa

Consensus maximisation learning can provide self-supervision when different views are available of the same data. The distributional hypothesis provides another form of useful self-supervision from adjacent sentences whi…

Self-Supervised LearningSentence