In this paper, we propose deformable deep convolutional neural networks for
generic object detection. This new deep learning object detection framework has
innovations in multiple aspects. In the proposed new deep architecture, a new
deformation constrained pooling (def-pooling) layer models the deformation of
object parts with geometric constraint and penalty. A new pre-training strategy
is proposed to learn feature representations more suitable for the object
detection task and with good generalization capability. By changing the net
structures, training strategies, adding and removing some key components in the
detection pipeline, a set of models with large diversity are obtained, which
significantly improves the effectiveness of model averaging. The proposed
approach improves the mean averaged precision obtained by RCNN
\cite{girshick2014rich}, which was the state-of-the-art, from 31\% to 50.3\% on
the ILSVRC2014 detection test set. It also outperforms the winner of
ILSVRC2014, GoogLeNet, by 6.1\%. Detailed component-wise analysis is also
provided through extensive experimental evaluation, which provide a global view
for people to understand the deep learning object detection pipeline.

本文提出了一种新的深度学习目标检测框架，引入了变形卷积神经网络、约束池化层等创新，通过组合不同的网络结构和组件、改变训练方法等方式，提高了模型的泛化能力和检测精度，实验结果表明该方法在 ILSVRC2014 比赛中的表现明显优于 RCNN 和 GoogleNet，能有效提升目标检测效果。

DeepID-Net: 可变形深度卷积神经网络用于目标检测

DeepID-Net: Deformable Deep Convolutional Neural Networks for Object  Detection

The model averaging problem is to average multiple models to achieve a
prediction accuracy not much worse than that of the best single model in terms
of mean squared error. It is known that if the models are misspecified, model
averaging is superior to model selection. Specifically, let $n$ be the sample
size, then the worst case regret of the former decays at a rate of $O(1/n)$
while the worst case regret of the latter decays at a rate of $O(1/\sqrt{n})$.
The recently proposed $Q$-aggregation algorithm \citep{DaiRigZhang12} solves
the model averaging problem with the optimal regret of $O(1/n)$ both in
expectation and in deviation; however it suffers from two limitations: (1) for
continuous dictionary, the proposed greedy algorithm for solving
$Q$-aggregation is not applicable; (2) the formulation of $Q$-aggregation
appears ad hoc without clear intuition. This paper examines a different
approach to model averaging by considering a Bayes estimator for deviation
optimal model averaging by using exponentiated least squares loss. We establish
a primal-dual relationship of this estimator and that of $Q$-aggregation and
propose new greedy procedures that satisfactorily resolve the above mentioned
limitations of $Q$-aggregation.

本文探讨采用贝叶斯估计器与指数化最小二乘损失来进行偏差最优的模型平均，通过建立两种方法之间的原始对偶关系并提出新的贪心方法，规避了现有 $Q$- 聚合算法的局限性。

指数最小平方损失贝叶斯模型平均

Bayesian Model Averaging with Exponentiated Least Square Loss

As an alternative to variable selection or shrinkage in high dimensional
regression, we propose to randomly compress the predictors prior to analysis.
This dramatically reduces storage and computational bottlenecks, performing
well when the predictors can be projected to a low dimensional linear subspace
with minimal loss of information about the response. As opposed to existing
Bayesian dimensionality reduction approaches, the exact posterior distribution
conditional on the compressed data is available analytically, speeding up
computation by many orders of magnitude while also bypassing robustness issues
due to convergence and mixing problems with MCMC. Model averaging is used to
reduce sensitivity to the random projection matrix, while accommodating
uncertainty in the subspace dimension. Strong theoretical support is provided
for the approach by showing near parametric convergence rates for the
predictive density in the large p small n asymptotic paradigm. Practical
performance relative to competitors is illustrated in simulations and real data
applications.

本文提出一种基于随机压缩预测变量的高维回归方法，并使用模型平均来减少方法对于随机投影矩阵的敏感度，可用于实际数据应用。

贝叶斯压缩回归

Bayesian Compressed Regression

We consider the problem of designing models to leverage a recently introduced
approximate model averaging technique called dropout. We define a simple new
model called maxout (so named because its output is the max of a set of inputs,
and because it is a natural companion to dropout) designed to both facilitate
optimization by dropout and improve the accuracy of dropout's fast approximate
model averaging technique. We empirically verify that the model successfully
accomplishes both of these tasks. We use maxout and dropout to demonstrate
state of the art classification performance on four benchmark datasets: MNIST,
CIFAR-10, CIFAR-100, and SVHN.

该研究提出了一种名为 maxout 的新型神经网络结构，它可以利用所谓的 dropout 技术中的近似模型平均方法进行优化，并提高快速近似模型平均方法的准确性，同时在四个基准数据集（MNIST，CIFAR-10，CIFAR-100 和 SVHN）上展示了最先进的分类性能。