Using Split-Brain autoencoders to learn an unsupervised representation of visual saliency in scenes

使用裂脑自动编码器学习场景中视觉显着性的无监督表示

• 批准号: 1929930
• 金额: --
• 依托单位: University of Edinburgh
• 依托单位国家: 英国
• 项目类别: Studentship
• 财政年份: 2017
• 资助国家: 英国
• 起止时间: 2017 至 无数据
• 项目状态: 已结题
• 来源: https://gtr.ukri.org/projects?ref=studentship-1929930
• 关键词: Using; Split; Brain; autoencoders; learn

This research focuses on unsupervised methods of predicting the visual saliency of regions of scenes. We use a split brain auto-encoder model in which two auto-encoders - each representing a 'hemisphere' - are trained to predict the output of the other. This is an extension of the predictive processing model of cognition. According to our model, each hemisphere is engaged in attempting to predict the output of the other and in order to do so, must learn useful representations of the input.If successful, this research will provide a useful unsupervised method of predicting visual saliency in scenes, as well as improve our understanding of how the brain is able to extract information out of the jumble of input it receives, as well as the importance of hemisphericity as an organising principle of the brain.Project milestones are as follows: 1.) Conduct a literature review and identify relevant work and similar approaches. 2.) Create a working prototype system3.) Compare the performance of the system on eye-tracking data with maps of visual saliency across scenes, for example the MIT dataset.4.) Iterate and improve the model and report on findings.

本研究的重点是预测场景区域的视觉显著性的无监督方法。我们使用了一个裂脑自动编码器模型，其中两个自动编码器-每个代表一个“半球”-被训练来预测另一个的输出。这是认知的预测处理模型的延伸。根据我们的模型，每个半球都在试图预测另一个半球的输出，为了做到这一点，必须学习输入的有用表示。如果成功，这项研究将提供一种有用的无监督方法来预测场景中的视觉显着性，并提高我们对大脑如何能够从接收到的混乱输入中提取信息的理解，以及半球性作为大脑组织原则的重要性。项目里程碑如下：1.进行文献审查，并确定相关的工作和类似的方法。2.）的情况。创建一个工作原型系统3.）将系统在眼动追踪数据上的性能与跨场景的视觉显著性地图进行比较，例如MIT的地图。迭代和改进模型并报告发现。

项目成果

Combining Active Inference and Hierarchical Predictive Coding: A Tutorial Introduction and Case Study

主动推理和分层预测编码的结合：教程介绍和案例研究

• DOI: 10.31234/osf.io/kf6wc
• 发表时间: 2019
• 作者: Millidge B

Vocal imitation can create acoustic attractors to guide mothers to pups in a crowded colony of Mexican free-tailed bats: A case-study of computational modelling in behavioural biology

声音模仿可以产生声学吸引子，引导母亲在拥挤的墨西哥无尾蝙蝠群体中寻找幼崽：行为生物学计算模型的案例研究

• DOI: 10.31234/osf.io/9y652
• 发表时间: 2019
• 作者: Shillcock R

Fixational Eye Movements: Data Augmentation for the Brain?

固定眼动：大脑的数据增强？

• DOI: 10.31234/osf.io/vymzp
• 发表时间: 2019
• 作者: Millidge B

A Predictive Processing Account of Bottom-Up Visual Saliency Using Cross-Predicting Autoencoders

使用交叉预测自动编码器的自下而上视觉显着性的预测处理帐户

• DOI: 10.31234/osf.io/csmeb
• 发表时间: 2018
• 作者: Millidge B

Implementing Predictive Processing and Active Inference: Preliminary Steps and Results

实施预测处理和主动推理：初步步骤和结果

• DOI: 10.31234/osf.io/4hb58
• 发表时间: 2019
• 作者: Millidge B