To tackle such an issue as well as promote the quality of object attention, we introduce asimple yet effectiveSelfErasing Network (SeeNet) to prohibit attentions from spreading to unexpected background regions.

This work is conducted at Microsoft Research Asia.

This paper studies the use of a machine learning-based estimator as a control variate for mitigating the variance of Monte Carlo sampling. Specifically, we seek to uncover the key factors that influence the efficiency of control variates in reducing variance.

Many applications require computing likelihoods and marginal probabilities over a distribution defined by a graphical model, tasks which are intractable in general [24].

Work done during an internship at Baidu Inc.