Summary of related papers on visual attention. Related code will be released based on Jittor gradually.

Improving Convolutional Networks via Attention Transfer (ICLR 2017)

External Attention Network

🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

The official pytorch implemention of our ICML-2021 paper "SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks".

Code for our CVPR2021 paper coordinate attention

FcaNet: Frequency Channel Attention Networks

Implementing Stand-Alone Self-Attention in Vision Models using Pytorch

We design an effective Relation-Aware Global Attention (RGA) module for CNNs to globally infer the attention.

Official PyTorch Implementation for "Rotate to Attend: Convolutional Triplet Attention Module." [WACV 2021]

Code/Model release for NIPS 2017 paper "Attentional Pooling for Action Recognition"

Code for ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks

FcaNet: Frequency Channel Attention Networks

list of efficient attention modules

Code for AutoNL on ImageNet (CVPR2020)

Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition (https://arxiv.org/pdf/2006.11538.pdf)

Awesome List of Attention Modules and Plug&Play Modules in Computer Vision

Dual Attention Network for Scene Segmentation (CVPR2019)

[arXiv 2020] Deep Connected Attention Networks

ResNeSt: Split-Attention Networks

Keras Attention Layer (Luong and Bahdanau scores).

BiSeNet based on pytorch

GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond

Implementation of Non-local Block.

PyTorch implementation of SENet

Official PyTorch code for "BAM: Bottleneck Attention Module (BMVC2018)" and "CBAM: Convolutional Block Attention Module (ECCV2018)"

[ICCV W] Contextual Convolutional Neural Networks (https://arxiv.org/pdf/2108.07387.pdf)

PyTorch code for our paper : "SRM : A Style-based Recalibration Module for Convolutional Neural Networks" (https://arxiv.org/abs/1903.10829)