DeepLabv1是在2015年发表，在此之前，图像分类、目标检测、语义分割等都基于DCNN模型发展，但DCNN会存在重复池化导致分辨率下降；位置信息丢失，难以恢复，分割结果粗糙，丢失细节等问题；故DeepLab系列对DCNN等问题进行改进。

DeepLab v1

论文：Semantic image segmentation with deep convolutional nets and fully connected CRFs

DeepLab v2

论文：DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

DeepLab v3

论文：Rethinking Atrous Convolution for SemanticImage Segmentation

DeepLab v3+

论文：Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation