All Projects → pprp → Awesome Attention Mechanism In Cv

pprp / Awesome Attention Mechanism In Cv

Licence: mit
计算机视觉中用到的注意力模块和其他即插即用模块PyTorch Implementation Collection of Attention Module and Plug&Play Module

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Awesome Attention Mechanism In Cv

Mspeekcollectionviewdelegateimplementation
A custom paging behavior that peeks the previous and next items in a collection view
Stars: ✭ 265 (+390.74%)
Mutual labels:  implementation
Structured Self Attention
A Structured Self-attentive Sentence Embedding
Stars: ✭ 459 (+750%)
Mutual labels:  attention-model
100 Days Of Ml Code
100 Days of ML Coding
Stars: ✭ 33,641 (+62198.15%)
Mutual labels:  implementation
Attention ocr.pytorch
This repository implements the the encoder and decoder model with attention model for OCR
Stars: ✭ 278 (+414.81%)
Mutual labels:  attention-model
100daysofmlcode
Stars: ✭ 387 (+616.67%)
Mutual labels:  implementation
Dnc Tensorflow
A TensorFlow implementation of DeepMind's Differential Neural Computers (DNC)
Stars: ✭ 587 (+987.04%)
Mutual labels:  implementation
unity-dijkstras-pathfinding
Dijkstra's Pathfinding Algorithm Unity Implementation. (Not being maintained by me, it is just an experiment.)
Stars: ✭ 80 (+48.15%)
Mutual labels:  implementation
Sockeye
Sequence-to-sequence framework with a focus on Neural Machine Translation based on Apache MXNet
Stars: ✭ 990 (+1733.33%)
Mutual labels:  attention-model
Attention Ocr Chinese Version
Attention OCR Based On Tensorflow
Stars: ✭ 421 (+679.63%)
Mutual labels:  attention-model
Esfnet Pytorch
ESFNet-Pytorch
Stars: ✭ 18 (-66.67%)
Mutual labels:  implementation
Transformer
A TensorFlow Implementation of the Transformer: Attention Is All You Need
Stars: ✭ 3,646 (+6651.85%)
Mutual labels:  implementation
Mtan
The implementation of "End-to-End Multi-Task Learning with Attention" [CVPR 2019].
Stars: ✭ 364 (+574.07%)
Mutual labels:  attention-model
Gpt 2 Pytorch
Simple Text-Generator with OpenAI gpt-2 Pytorch Implementation
Stars: ✭ 618 (+1044.44%)
Mutual labels:  implementation
Ml implementation
Implementation of Machine Learning Algorithms
Stars: ✭ 279 (+416.67%)
Mutual labels:  implementation
Dcgan Pytorch
PyTorch Implementation of DCGAN trained on the CelebA dataset.
Stars: ✭ 32 (-40.74%)
Mutual labels:  implementation
Ethereum Erc721
Non-fungible token implementation for Ethereum-based blockchains.
Stars: ✭ 253 (+368.52%)
Mutual labels:  implementation
Nmt Keras
Neural Machine Translation with Keras
Stars: ✭ 501 (+827.78%)
Mutual labels:  attention-model
Authenticationservice
Implementations for JWT Authentication in C# and NodeJS.
Stars: ✭ 47 (-12.96%)
Mutual labels:  implementation
Reading comprehension tf
Machine Reading Comprehension in Tensorflow
Stars: ✭ 37 (-31.48%)
Mutual labels:  attention-model
Text Classification Pytorch
Text classification using deep learning models in Pytorch
Stars: ✭ 683 (+1164.81%)
Mutual labels:  attention-model

Awesome-Attention-Mechanism-in-cv Awesome

Table of Contents

Introduction

PyTorch实现多种计算机视觉中网络设计中用到的Attention机制,还收集了一些即插即用模块。由于能力有限精力有限,可能很多模块并没有包括进来,有任何的建议或者改进,可以提交issue或者进行PR。

Attention Mechanism

Paper Publish Link Main Idea Blog
Global Second-order Pooling Convolutional Networks CVPR19 GSoPNet 将高阶和注意力机制在网络中部地方结合起来
Neural Architecture Search for Lightweight Non-Local Networks CVPR20 AutoNL NAS+LightNL
Squeeze and Excitation Network CVPR18 SENet 最经典的通道注意力 zhihu
Selective Kernel Network CVPR19 SKNet SE+动态选择 zhihu
Convolutional Block Attention Module ECCV18 CBAM 串联空间+通道注意力 zhihu
BottleNeck Attention Module BMVC18 BAM 并联空间+通道注意力 zhihu
Concurrent Spatial and Channel ‘Squeeze & Excitation’ in Fully Convolutional Networks MICCAI18 scSE 并联空间+通道注意力 zhihu
Non-local Neural Networks CVPR19 Non-Local(NL) self-attention zhihu
GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond ICCVW19 GCNet 对NL进行改进 zhihu
CCNet: Criss-Cross Attention for Semantic Segmentation ICCV19 CCNet 对NL改进
SA-Net:shuffle attention for deep convolutional neural networks ICASSP 21 SANet SGE+channel shuffle zhihu
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks CVPR20 ECANet SE的改进
Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks CoRR19 SGENet Group+spatial+channel
FcaNet: Frequency Channel Attention Networks CoRR20 FcaNet 频域上的SE操作
$A^2\text{-}Nets$: Double Attention Networks NeurIPS18 DANet NL的思想应用到空间和通道
Asymmetric Non-local Neural Networks for Semantic Segmentation ICCV19 APNB spp+NL
Efficient Attention: Attention with Linear Complexities CoRR18 EfficientAttention NL降低计算量
Image Restoration via Residual Non-local Attention Networks ICLR19 RNAN
Exploring Self-attention for Image Recognition CVPR20 SAN 理论性很强,实现起来很简单
An Empirical Study of Spatial Attention Mechanisms in Deep Networks ICCV19 None MSRA综述self-attention
Object-Contextual Representations for Semantic Segmentation ECCV20 OCRNet 复杂的交互机制,效果确实好
IAUnet: Global Context-Aware Feature Learning for Person Re-Identification TTNNLS20 IAUNet 引入时序信息
ResNeSt: Split-Attention Networks CoRR20 ResNeSt SK+ResNeXt
Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks NeurIPS18 GENet SE续作
Improving Convolutional Networks with Self-calibrated Convolutions CVPR20 SCNet 自校正卷积
Rotate to Attend: Convolutional Triplet Attention Module WACV21 TripletAttention CHW两两互相融合
Dual Attention Network for Scene Segmentation CVPR19 DANet self-attention
Relation-Aware Global Attention for Person Re-identification CVPR20 RGA 用于reid
Attentional Feature Fusion WACV21 AFF 特征融合的attention方法
An Attentive Survey of Attention Models CoRR19 None 包括NLP/CV/推荐系统等方面的注意力机制
Stand-Alone Self-Attention in Vision Models NeurIPS19 FullAttention 全部的卷积都替换为self-attention
BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation ECCV18 BiSeNet 类似FPN的特征融合方法 zhihu
DCANet: Learning Connected Attentions for Convolutional Neural Networks CoRR20 DCANet 增强attention之间信息流动
An Empirical Study of Spatial Attention Mechanisms in Deep Networks ICCV19 None 对空间注意力进行针对性分析
Look closer to see better: Recurrent attention convolutional neural network for fine-grained image recognition CVPR17 Oral RA-CNN 细粒度识别
Guided Attention Network for Object Detection and Counting on Drones ACM MM20 GANet 处理目标检测问题
Attention Augmented Convolutional Networks ICCV19 AANet 多头+引入额外特征映射
GLOBAL SELF-ATTENTION NETWORKS FOR IMAGE RECOGNITION ICLR21 GSA 新的全局注意力模块
Attention-Guided Hierarchical Structure Aggregation for Image Matting CVPR20 HAttMatting 抠图方面的应用,高层使用通道注意力机制,然后再使用空间注意力机制指导低层。
Weight Excitation: Built-in Attention Mechanisms in Convolutional Neural Networks ECCV20 None 与SE互补的权值激活机制
Expectation-Maximization Attention Networks for Semantic Segmentation ICCV19 Oral EMANet EM+Attention
Dense-and-implicit attention network AAAI 20 DIANet LSTM+全程SE注意力
Coordinate Attention for Efficient Mobile Network Design CVPR21 CoordAttention 横向、竖向
Cross-channel Communication Networks NIPS19 C3Net GNN+SE

Plug and Play Module

  • ACBlock
  • Swish、wish Activation
  • ASPP Block
  • DepthWise Convolution
  • Fused Conv & BN
  • MixedDepthwise Convolution
  • PSP Module
  • RFBModule
  • SematicEmbbedBlock
  • SSH Context Module
  • Some other usefull tools such as concate feature map、flatten feature map
  • WeightedFeatureFusion:EfficientDet中的FPN用到的fuse方式
  • StripPooling:CVPR2020中核心代码StripPooling
  • GhostModule: CVPR2020GhostNet的核心模块
  • SlimConv: SlimConv3x3
  • Context Gating: video classification
  • EffNetBlock: EffNet
  • ECCV2020 BorderDet: Border aligment module
  • CVPR2019 DANet: Dual Attention
  • Object Contextual Representation for sematic segmentation: OCRModule
  • FPT: 包含Self Transform、Grounding Transform、Rendering Transform
  • DOConv: 阿里提出的Depthwise Over-parameterized Convolution
  • PyConv: 起源人工智能研究院提出的金字塔卷积
  • ULSAM:用于紧凑型CNN的超轻量级子空间注意力模块
  • DGC: ECCV 2020用于加速卷积神经网络的动态分组卷积
  • DCANet: ECCV 2020 学习卷积神经网络的连接注意力
  • PSConv: ECCV 2020 将特征金字塔压缩到紧凑的多尺度卷积层中
  • Dynamic Convolution: CVPR2020 动态滤波器卷积(非官方)
  • CondConv: Conditionally Parameterized Convolutions for Efficient Inference

Evaluation

基于CIFAR10+ResNet+待测评模块,对模块进行初步测评。测评代码来自于另外一个库:https://github.com/kuangliu/pytorch-cifar/ 实验过程中,不使用预训练权重,进行随机初始化。

模型 top1 acc time params(MB)
SENet18 95.28% 1:27:50 11,260,354
ResNet18 95.16% 1:13:03 11,173,962
ResNet50 95.50% 4:24:38 23,520,842
ShuffleNetV2 91.90% 1:02:50 1,263,854
GoogLeNet 91.90% 1:02:50 6,166,250
MobileNetV2 92.66% 2:04:57 2,296,922
SA-ResNet50 89.83% 2:10:07 23,528,758
SA-ResNet18 95.07% 1:39:38 11,171,394

Paper List

SENet 论文: https://arxiv.org/abs/1709.01507 解读:https://zhuanlan.zhihu.com/p/102035721

参考

ATPaper库

Contribute

欢迎在issue中提出补充的文章paper和对应code链接。

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].