# Brief Review — An Improved U-Net Method for Sequence Images Segmentation

## Improved U-Net, Using Multi-Scale Convolution

@ Medium)

An Improved U-Net Method for Sequence Images Segmentation,Improved U-Net, by Guilin University of Electronic and Technology,2019 ICACI(

Image Segmentation, Semantic Segmentation, U-Net

- An
**Improved U-Net**is proposed where**multi-scale convolution modules**are added on the basis of U-Net structure to**increase the network depth**and**improve feature extraction capability.**The**batch normalization (****BN****)**layer is added to accelerate the speed of converged network. - A
**heat-map channel**is added in the**input**data to prevent errors of classification in similar areas.

# Outline

**Improved****U-Net****Results**

**1. Improved **U-Net

## 1.1. Overall Architecture

- The U-Net-like model is used as above with the use of
**Multiscale Convolution Module (Blocks with cross pattern).**

## 1.2. Multiscale Convolution Module

- The convolution
**kernel is fixed in size in the original****U-Net**. - If it is
**too small**, the**global information is lost.** - If it is
**too large**, the field of view is too large, so that the extracted features**cannot obtain effective local information**. **The Multiscale Convolution Module**composed of**a 3×3 convolution****kernel, a 5×5 convolution kernel,**and a multi-scale convolution layer composed of a**maximum pooling layer**, inspired by Inception Module in**GoogLeNet**.

## 1.3. Loss Function

- The
**binary cross-entropy**is used as the loss function:

## 1.4. Heat-Map Channel

**Image saliency detection method**is applied to generate heat map channel as input.- Particularly, the
**CA (Context-Aw) algorithm**proposes a context-aware saliency measurement method that makes**the color-dense region highly visible**, while the**region with****low color density**has a**low significance value**. - First,
**the distance between the patches is calculated**by the following formula:

- where
and*i*are*k***two pixel points**respectively,and*pi*are*pk**r*pixel blocks around points*i*and*k**c*is constant 3,is the*dcolor*(*pi*,*pk*)**color distance between the patches**, andis the*dposition*(*pi*,*pk*)**spatial distance between the patches.** **The significant value at the single scale**according to the patch distance is calculated:

- The significant value on the
**multi-scale**and**take the mean value**to get the final significant value:

- where
**4 scales of**= {1, 0.8, 0.5, 0.3} are used.*R*

After

adding the heat-map channel, it caneffectively constrain the segmentation area of the network.

# 2. Results

The

improvedU-Netmethod gives amuch better improvement in the edgeof the target, producing asmoother edgeandstronger generalization ability.

## Reference

[2019 ICACI] [Improved U-Net]

An Improved U-Net Method for Sequence Images Segmentation

## 1.5. Semantic Segmentation / Scene Parsing

**2015** … **2019** … [Improved U-Net] … **2020** [DRRN Zhang JNCA’20] [Trans10K, TransLab] [CCNet] **2021** [PVT, PVTv1] [SETR] [Trans10K-v2, Trans2Seg] **2022 **[PVTv2]