Network in Network (NiN)

This novel deep network structure called "Network In Network" (NIN) to enhance model discriminability for local patches within the receptive field. The conventional convolutional layer uses linear filters followed by a nonlinear activation function to scan the input. Instead, build micro neural networks with more complex structures to abstract the data within the receptive field.

DeeplearningAI

true

Contributor(s)

Initial contribute: 2020-12-05

Authorship

Is authorship not correct? Feed back

Classification(s)

Method-focused categoriesData-perspectiveIntelligent computation analysis

Detailed Description

English {{currentDetailLanguage}} English

Quoted from: https://arxiv.org/abs/1312.4400

The inputs and outputs of convolutional layers consist of four-dimensional tensors with axes corresponding to the example, channel, height, and width. The inputs and outputs of fully-connected layers are typically two-dimensional tensors corresponding to the example and feature. The idea behind NiN is to apply a fully-connected layer at each pixel location (for each height and width). If we tie the weights across each spatial location, we could think of this as a  1×1  convolutional layer (as described in Section 6.4) or as a fully-connected layer acting independently on each pixel location. Another way to view this is to think of each element in the spatial dimension (height and width) as equivalent to an example and a channel as equivalent to a feature.

The following figure illustrates the main structural differences between VGG and NiN, and their blocks. The NiN block consists of one convolutional layer followed by two  1×1  convolutional layers that act as per-pixel fully-connected layers with ReLU activations. The convolution window shape of the first layer is typically set by the user. The subsequent window shapes are fixed to  1×1 .

../_images/nin.svg

模型元数据

{{htmlJSON.HowtoCite}}

Min Lin (2020). Network in Network (NiN), Model Item, OpenGMS, https://geomodeling.njnu.edu.cn/modelItem/d26de6cb-3af2-42a5-aaa1-1a43d9c40952
{{htmlJSON.Copy}}

Contributor(s)

Initial contribute : 2020-12-05

{{htmlJSON.CoContributor}}

Authorship

Is authorship not correct? Feed back

QR Code

×

{{curRelation.overview}}
{{curRelation.author.join('; ')}}
{{curRelation.journal}}









{{htmlJSON.RelatedItems}}

{{htmlJSON.LinkResourceFromRepositoryOrCreate}}{{htmlJSON.create}}.

Drop the file here, orclick to upload.
Select From My Space
+ add

{{htmlJSON.authorshipSubmitted}}

Cancel Submit
{{htmlJSON.Cancel}} {{htmlJSON.Submit}}
{{htmlJSON.Localizations}} + {{htmlJSON.Add}}
{{ item.label }} {{ item.value }}
{{htmlJSON.ModelName}}:
{{htmlJSON.Cancel}} {{htmlJSON.Submit}}
名称 别名 {{tag}} +
系列名 版本号 目的 修改内容 创建/修改日期 作者
摘要 详细描述
{{tag}} + 添加关键字
* 时间参考系
* 空间参考系类型 * 空间参考系名称

起始日期 终止日期 进展 开发者
* 是否开源 * 访问方式 * 使用方式 开源协议 * 传输方式 * 获取地址 * 发布日期 * 发布者



编号 目的 修改内容 创建/修改日期 作者





时间分辨率 时间尺度 时间步长 时间范围 空间维度 格网类型 空间分辨率 空间尺度 空间范围
{{tag}} +
* 类型
图例


* 名称 * 描述
示例描述 * 名称 * 类型 * 值/链接 上传


{{htmlJSON.Cancel}} {{htmlJSON.Submit}}
Title Author Date Journal Volume(Issue) Pages Links Doi Operation
{{htmlJSON.Cancel}} {{htmlJSON.Submit}}
{{htmlJSON.Add}} {{htmlJSON.Cancel}}

{{articleUploading.title}}

Authors:  {{articleUploading.authors[0]}}, {{articleUploading.authors[1]}}, {{articleUploading.authors[2]}}, et al.

Journal:   {{articleUploading.journal}}

Date:   {{articleUploading.date}}

Page range:   {{articleUploading.pageRange}}

Link:   {{articleUploading.link}}

DOI:   {{articleUploading.doi}}

Yes, this is it Cancel

The article {{articleUploading.title}} has been uploaded yet.

OK
{{htmlJSON.Cancel}} {{htmlJSON.Confirm}}