Alternatives and similar repositories for backbone:

Users that are interested in backbone are comparing it to the libraries listed below

• YOLOonMe / EMA-attention-module
  Implementation Code for the ICCASSP 2023 paper " Efficient Multi-Scale Attention Module with Cross-Spatial Learning" and is available at:…
  ☆231Updated 3 months ago
• cheng-haha / ScConv
  🕹️SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy
  ☆303Updated 7 months ago
• apple1986 / HWD
  A Simple but Effective Downsampling Module For Semantic Segmentation
  ☆109Updated last year
• ndsclark / MCANet
  The official PyTorch implementation of our paper "MCA: Multidimensional collaborative attention in deep convolutional neural networks for…
  ☆59Updated last year
• CV-Tech-Guide / Visualize-feature-maps-and-heatmap
  可视化特征图教程
  ☆72Updated 3 years ago
• AfifaKhaled / Batch-Channel-Normalization
  ☆36Updated last year
• lhj7670915851 / CBAM-CycleGAN
  神经网络与深度学习大作业
  ☆17Updated 3 years ago
• ZhugeKongan / Attention-mechanism-implementation
  Self-attention、Non-local、SE、SK、CBAM、DANet
  ☆469Updated 3 years ago
• youwh-PIRI / fpn_resnet-resnet-se-resnet-cbam
  fpn_resnet、resnet-se、resnet-cbam
  ☆33Updated 5 years ago
• xiely-123 / SHISRCNet
  ☆39Updated last year
• 974938429 / Grad-CAM
  可视化神经网络
  ☆38Updated 2 years ago
• LMMMEng / TransXNet
  [TNNLS 2025] TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognition
  ☆175Updated last week
• sunanlin13174 / Image-train-Swin-transformer
  基于Swin-transformer训练图像分类并部署web端
  ☆89Updated 2 years ago
• murufeng / EPSANet
  ☆298Updated 3 years ago
• HNzhaoyli / attention-module
  深度学习 注意力机制模块 时间 空间注意力通道
  ☆29Updated last year
• bubbliiiing / classification-pytorch
  这是各个主干网络分类模型的源码，可以用于训练自己的分类模型。
  ☆422Updated 2 years ago
• northBeggar / Plug-and-Play
  深度学习中各种即插即用小模块
  ☆380Updated last year
• bubbliiiing / dcgan-pytorch
  这是一个dcgan-pytorch的源码，可以用于训练自己的模型。
  ☆58Updated 2 years ago
• HZAI-ZJNU / SCSA
  The official pytorch implementation of "SCSA: Exploring the Synergistic Effects Between Spatial and Channel Attention".
  ☆71Updated 3 weeks ago
• qhfan / CloFormer
  The official code of "Rethinking Local Perception in Lightweight Vision Transformer"
  ☆86Updated last year
• JIAOJIAYUASD / dilateformer
  ☆144Updated last year
• huoxiangzuo / HiFuse
  HiFuse: Hierarchical Multi-Scale Feature Fusion Network for Medical Image Classification
  ☆225Updated 3 months ago
• gorkemcanates / Dual-Cross-Attention
  Official Pytorch implementation of Dual Cross-Attention for Medical Image Segmentation
  ☆128Updated 6 months ago
• cecret3350 / DEA-Net
  [IEEE TIP 2024] DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention
  ☆303Updated 3 months ago
• woosual / multiModalityFusionForClassification
  多模态数据融合：为了完成多模态数据融合，首先利用VGG16网络和cifar10数据集完成多输入网络的分类，在VGG16的基础之上，将前三层特征提取网络作为不同输入的特征提取网络，在中间层进行特征拼接，后面的卷积层用于提取融合特征，最后加上全连接层。该网络稍作修改就能同时提取…
  ☆88Updated 4 years ago
• Cuthbert-Huang / CPCANet
  ☆60Updated last year
• CPones / Classification-12Cat-ResNet-and-ViT
  细粒度图像分类之十二猫分类，对比ResNet和ViT两者模型性能。
  ☆45Updated 3 years ago
• xiaoqiang765 / MLSummary
  ☆21Updated 2 years ago
• mmasterer / VGG16
  ☆17Updated 2 years ago
• multimediaFor / ConvNeXtFF
  Source code of the paper: Effective Image Tampering Localization with Multi-Scale ConvNeXt Feature Fusion, JVCIR 2024.
  ☆32Updated last year