We investigate the problem of cross-dataset adaptation for visual question
answering (Visual QA). Our goal is to train a Visual QA model on a source
dataset but apply it to another target one. Analogous to domain adaptation for
visual recognition, this setting is appealing when the target dataset does not
have a sufficient amount of labeled data to learn an "in-domain" model. The key
challenge is that the two datasets are constructed differently, resulting in
the cross-dataset mismatch on images, questions, or answers.
We overcome this difficulty by proposing a novel domain adaptation algorithm.
Our method reduces the difference in statistical distributions by transforming
the feature representation of the data in the target dataset. Moreover, it
maximizes the likelihood of answering questions (in the target dataset)
correctly using the Visual QA model trained on the source dataset. We
empirically studied the effectiveness of the proposed approach on adapting
among several popular Visual QA datasets. We show that the proposed method
improves over baselines where there is no adaptation and several other
adaptation methods. We both quantitatively and qualitatively analyze when the
adaptation can be mostly effective.

本研究提出了一种新颖的域自适应算法，通过转换目标数据集的特征，减少统计分布上的差异，以训练源数据集的视觉问答模型，最大化对目标数据集上的问题正确回答的可能性。通过在几个热门的视觉问答数据集之间进行适应性调整的实证研究，发现所提出的方法优于没有适应和其他方法，并定量和 qualitatively 分析了适应性何时最为有效。

视觉问答的跨数据集自适应

Cross-Dataset Adaptation for Visual Question Answering

A novel framework of compressed sensing, namely statistical compressed
sensing (SCS), that aims at efficiently sampling a collection of signals that
follow a statistical distribution, and achieving accurate reconstruction on
average, is introduced. SCS based on Gaussian models is investigated in depth.
For signals that follow a single Gaussian model, with Gaussian or Bernoulli
sensing matrices of O(k) measurements, considerably smaller than the O(k
log(N/k)) required by conventional CS based on sparse models, where N is the
signal dimension, and with an optimal decoder implemented via linear filtering,
significantly faster than the pursuit decoders applied in conventional CS, the
error of SCS is shown tightly upper bounded by a constant times the best k-term
approximation error, with overwhelming probability. The failure probability is
also significantly smaller than that of conventional sparsity-oriented CS.
Stronger yet simpler results further show that for any sensing matrix, the
error of Gaussian SCS is upper bounded by a constant times the best k-term
approximation with probability one, and the bound constant can be efficiently
calculated. For Gaussian mixture models (GMMs), that assume multiple Gaussian
distributions and that each signal follows one of them with an unknown index, a
piecewise linear estimator is introduced to decode SCS. The accuracy of model
selection, at the heart of the piecewise linear decoder, is analyzed in terms
of the properties of the Gaussian distributions and the number of sensing
measurements. A maximum a posteriori expectation-maximization algorithm that
iteratively estimates the Gaussian models parameters, the signals model
selection, and decodes the signals, is presented for GMM-based SCS. In real
image sensing applications, GMM-based SCS is shown to lead to improved results
compared to conventional CS, at a considerably lower computational cost.

本研究提出了基于统计压缩感知（SCS）的压缩感知（CS）新框架，探索了基于高斯模型的 SCS，对单高斯模型下的信号进行了深入探究，并介绍了用于 GMM 型的信号模型选择、解码的分段线性估算器，提出了最大后验期望最大化算法用于 GMM 型 - SCS 的解码过程。结果表明，与传统 CS 相比，GMM 型 - SCS 在图像感知应用中具有更低的计算成本且具有更好的结果。

高斯混合模型的统计压缩感知

Statistical Compressed Sensing of Gaussian Mixture Models

Understanding the complexity of human language requires an appropriate
analysis of the statistical distribution of words in texts. We consider the
information retrieval problem of detecting and ranking the relevant words of a
text by means of statistical information referring to the "spatial" use of the
words. Shannon's entropy of information is used as a tool for automatic keyword
extraction. By using The Origin of Species by Charles Darwin as a
representative text sample, we show the performance of our detector and compare
it with another proposals in the literature. The random shuffled text receives
special attention as a tool for calibrating the ranking indices.

本文通过统计文本中单词的空间使用情况，利用信息熵作为工具实现自动关键词提取，并以达尔文的《物种起源》为代表性文本样本进行性能测试和比较。