## AlexNet

(资料图片仅供参考)

[【第61篇】AlexNet：CNN开山之作](https://wanghao.blog.csdn.net/article/details/128503264)

## VGGNet

[【第1篇】VGG](https://wanghao.blog.csdn.net/article/details/120094424)

## GooLeNet系列

[【第2篇】GooLeNet](https://wanghao.blog.csdn.net/article/details/120110029)

[【第3篇】Inception V2](https://wanghao.blog.csdn.net/article/details/120148613)

[【第4篇】Inception V3](https://wanghao.blog.csdn.net/article/details/120156107)

[【第62篇】Inception-v4](https://wanghao.blog.csdn.net/article/details/128522765)

## ResNet

[【第5篇】ResNet](https://wanghao.blog.csdn.net/article/details/120178266)

## DenseNet

[【第10篇】DenseNet](https://wanghao.blog.csdn.net/article/details/120347118)

## Swin Transformer

[【第16篇】Swin Transformer](https://wanghao.blog.csdn.net/article/details/120724040)

[【第49篇】Swin Transformer V2：扩展容量和分辨率](https://wanghao.blog.csdn.net/article/details/127135297)

## MAE

[【第21篇】MAE（屏蔽自编码器是可扩展的视觉学习器）](https://wanghao.blog.csdn.net/article/details/121605608)

## CoAtNet

[【第22篇】CoAtNet：将卷积和注意力结合到所有数据大小上](https://wanghao.blog.csdn.net/article/details/121993729)

## ConvNeXtV1、V2

[【第25篇】力压Tramsformer，ConvNeXt成了CNN的希望](https://wanghao.blog.csdn.net/article/details/122451111)

[【第64篇】ConvNeXt V2论文翻译：ConvNeXt V2与MAE激情碰撞](https://wanghao.blog.csdn.net/article/details/128541957?spm=1001.2014.3001.5502)

## MobileNet系列

[【第26篇】MobileNets：用于移动视觉应用的高效卷积神经网络](https://wanghao.blog.csdn.net/article/details/122692846)

[【第27篇】MobileNetV2：倒置残差和线性瓶颈](https://wanghao.blog.csdn.net/article/details/122729844)

[【第28篇】搜索 MobileNetV3](https://wanghao.blog.csdn.net/article/details/122779006)

## MPViT

[【第29篇】MPViT：用于密集预测的多路径视觉转换器](https://wanghao.blog.csdn.net/article/details/122782937)

## VIT

[【第30篇】Vision Transformer](https://wanghao.blog.csdn.net/article/details/123695223)

## SWA

[【第32篇】SWA：平均权重导致更广泛的最优和更好的泛化](https://wanghao.blog.csdn.net/article/details/124409374)

## EfficientNet系列

[【第34篇】 EfficientNetV2：更快、更小、更强——论文翻译](https://wanghao.blog.csdn.net/article/details/117399085)

## MOBILEVIT

[【第35篇】MOBILEVIT：轻量、通用和适用移动设备的Vision Transformer](https://wanghao.blog.csdn.net/article/details/124546928)

## EdgeViTs

[【第37篇】EdgeViTs： 在移动设备上使用Vision Transformers 的轻量级 CNN](https://wanghao.blog.csdn.net/article/details/124730330)

## MixConv

[【第38篇】MixConv：混合深度卷积核](https://wanghao.blog.csdn.net/article/details/124779609)

## RepLKNet

[【第39篇】RepLKNet将内核扩展到 31x31：重新审视 CNN 中的大型内核设计](https://wanghao.blog.csdn.net/article/details/124875771)

## TransFG

[【第40篇】TransFG：用于细粒度识别的 Transformer 架构](https://wanghao.blog.csdn.net/article/details/124919932)

## ConvMAE

[【第41篇】ConvMAE：Masked Convolution 遇到 Masked Autoencoders](https://wanghao.blog.csdn.net/article/details/124988783)

## MicroNet

[【第42篇】MicroNet：以极低的 FLOP 实现图像识别](https://wanghao.blog.csdn.net/article/details/125177445)

## RepVGG 

[【第46篇】RepVGG ：让卷积再次伟大](https://wanghao.blog.csdn.net/article/details/126446922)

## MaxViT

[【第48篇】MaxViT：多轴视觉转换器](https://wanghao.blog.csdn.net/article/details/127064117)

## MAFormer

[【第53篇】MAFormer: 基于多尺度注意融合的变压器网络视觉识别](https://wanghao.blog.csdn.net/article/details/127492341)

## GhostNet系列

[【第56篇】GhostNet:廉价操作得到更多的特征](https://wanghao.blog.csdn.net/article/details/127981705)

[【第57篇】RepGhost:一个通过重新参数化实现硬件高效的Ghost模块](https://wanghao.blog.csdn.net/article/details/128090737)

## DEiT系列

[【第58篇】DEiT：通过注意力训练数据高效的图像transformer &蒸馏](https://wanghao.blog.csdn.net/article/details/128180419)

## MetaFormer

[【第59篇】MetaFormer实际上是你所需要的视觉](https://wanghao.blog.csdn.net/article/details/128281326)

## RegNet

[【第60篇】RegNet：设计网络设计空间](https://wanghao.blog.csdn.net/article/details/128339572)

# 注意力机制

[【第23篇】NAM：基于标准化的注意力模块](https://wanghao.blog.csdn.net/article/details/122092352)

# 物体检测

[【第6篇】SSD论文翻译和代码汇总](https://wanghao.blog.csdn.net/article/details/105788036)

[【第7篇】CenterNet](https://wanghao.blog.csdn.net/article/details/105593958)

[【第8篇】M2Det](https://wanghao.blog.csdn.net/article/details/105593927)

[【第9篇】YOLOX](https://wanghao.blog.csdn.net/article/details/119535667)

[【第11篇】微软发布的Dynamic Head，创造COCO新记录：60.6AP](https://wanghao.blog.csdn.net/article/details/120365468)

[【第12篇】Sparse R-CNN: End-to-End Object Detection with Learnable Proposals](https://wanghao.blog.csdn.net/article/details/120413137)

[【第13篇】CenterNet2论文解析，COCO成绩最高56.4mAP](https://wanghao.blog.csdn.net/article/details/120464708)

[【第14篇】UMOP](https://wanghao.blog.csdn.net/article/details/120506747)

[【第15篇】CBNetV2](https://wanghao.blog.csdn.net/article/details/120583025)

[【第19篇 】SE-SSD论文翻译](https://wanghao.blog.csdn.net/article/details/120875331)

[【第24篇】YOLOR：多任务的统一网络](https://wanghao.blog.csdn.net/article/details/122357992)

[【第31篇】探索普通视觉Transformer Backbones用于物体检测](https://wanghao.blog.csdn.net/article/details/123960815)

[【第36篇】CenterNet++ 用于对象检测](https://wanghao.blog.csdn.net/article/details/124623781)

[【第45篇】YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://wanghao.blog.csdn.net/article/details/126302859)

# 行人属性识别

[【第66篇】行人属性识别研究综述（一）](https://wanghao.blog.csdn.net/article/details/128736760)

[【第66篇】行人属性识别研究综述（二）](https://wanghao.blog.csdn.net/article/details/128736732)

# 行人跟踪

[【第47篇】BoT-SORT：强大的关联多行人跟踪](https://wanghao.blog.csdn.net/article/details/126890651)

[【第65篇】SMILEtrack:基于相似度学习的多目标跟踪](https://blog.csdn.net/hhhhhhhhhhwwwwwwwwww/article/details/128615947)

[【第70篇】DeepSort：论文翻译](https://wanghao.blog.csdn.net/article/details/129003397)

# OCR

[【第20篇】像人类一样阅读：自主、双向和迭代语言 场景文本识别建模](https://wanghao.blog.csdn.net/article/details/121313548)

[【第44篇】DBNet：具有可微分二值化的实时场景文本检测](https://wanghao.blog.csdn.net/article/details/125513523)

# 超分辨采样

[【第33篇】SwinIR](https://wanghao.blog.csdn.net/article/details/124434886)

# 弱光增强

## RetinexNet

[【第52篇】RetinexNet: Deep Retinex Decomposition for Low-Light Enhancement](https://wanghao.blog.csdn.net/article/details/127400091)

[【第50篇】迈向快速、灵活、稳健的微光图像增强](https://wanghao.blog.csdn.net/article/details/127211265)

# NLP

[【第17篇】TextCNN](https://wanghao.blog.csdn.net/article/details/120729088)

[【第18篇】Bert论文翻译](https://wanghao.blog.csdn.net/article/details/120864338)

# 多模态

[【第43篇】CLIP：从自然语言监督中学习可迁移的视觉模型](https://wanghao.blog.csdn.net/article/details/125452516)

# 知识蒸馏

[【第54篇】知识蒸馏：Distilling the Knowledge in a Neural Network](https://wanghao.blog.csdn.net/article/details/127808674)

# 剪枝

[【第55篇】剪枝算法：通过网络瘦身学习高效卷积网络](https://wanghao.blog.csdn.net/article/details/127871910)

# 智慧城市

[【第51篇】用于交通预测的时空交互动态图卷积网络](https://wanghao.blog.csdn.net/article/details/127306179)