We mimic the cognitive ability of Human perception, based on Bayesian
hypothesis, to recognize view-based 3D objects. We consider approximate
Bayesian (Empirical Bayesian) for perceptual inference for recognition. We
essentially handle computation with perception.

该论文研究通过拟合贝叶斯假设模拟人类感知能力，以识别基于视图的 3D 物体，并实现了感知计算。

贝叶斯大脑：利用感知计算来识别三维物体

Bayesian Brain: Computation with Perception to Recognize 3D Objects

We present a framework for efficient perceptual inference that explicitly
reasons about the segmentation of its inputs and features. Rather than being
trained for any specific segmentation, our framework learns the grouping
process in an unsupervised manner or alongside any supervised task. By
enriching the representations of a neural network, we enable it to group the
representations of different objects in an iterative manner. By allowing the
system to amortize the iterative inference of the groupings, we achieve very
fast convergence. In contrast to many other recently proposed methods for
addressing multi-object scenes, our system does not assume the inputs to be
images and can therefore directly handle other modalities. For multi-digit
classification of very cluttered images that require texture segmentation, our
method offers improved classification performance over convolutional networks
despite being fully connected. Furthermore, we observe that our system greatly
improves on the semi-supervised result of a baseline Ladder network on our
dataset, indicating that segmentation can also improve sample efficiency.

本文介绍了一种有效的感知推断框架，该框架能够显式地处理输入和特征的分割，并通过增强神经网络的表示能力并对对象表示进行迭代分组，以及对其分组迭代推理进行摊销从而实现了快速收敛，相比其他处理多物体场景的方法，该方法不假设输入为图像，因此可以直接处理其他模态，并在处理具有纹理分割的复杂图像时提供更好的分类性能。