dynamic-convolution

Pytorch!!!Pytorch!!!Pytorch!!! Dynamic Convolution: Attention over Convolution Kernels (CVPR-2020)

[CVPR 2025 Oral] OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels

[TNNLS 2025] TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognition

ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution (CVPR 2023)

🔥🔥A pytorch implementation of Dynamic Convolutional Layer in Dynamic Conditional Convolutional Network for Few-Shot Learning🔥🔥

Conditional Convolutions for Instance Segmentation, achives 37.1mAP on coco val

[IEEE TIP 2023] Scale-Arbitrary Invertible Image Downscaling (AIDN)

Code for [IEEE-TMI] Domain and Content Adaptive Convolution based Multi-Source Domain Generalization for Medical Image Segmentation.

Official PyTorch Implementation of paper EAN: Event Adaptive Network for Efficient Action Recognition https://arxiv.org/abs/2107.10771

Code for [MICCAI 2022] Domain Specific Convolution and High Frequency Reconstruction based Unsupervised Domain Adaptation for Medical Image Segmentation.

This is a fork of caffe added some useful layers, the original caffe site is https://github.com/BVLC/caffe.

GaPro: Box-Supervised 3D Point Cloud Instance Segmentation Using Gaussian Processes as Pseudo Labelers (ICCV 2023)

Conditional convolution (Dynamic convolution) in tensorflow2

DDistill-SR: Reparameterized Dynamic Distillation Network for Lightweight Image Super-Resolution (TMM 2023)

Source code of ACL 2023 Main Conference Paper "PAD-Net: An Efficient Framework for Dynamic Networks".

Context-Aware Dynamic Feature Extraction for 3D Object Detection in Point Clouds

Dynamic Convolution (training optimization)

HarvestNet 2.0: Improved Detection of Harvest Piles in Ethiopia

Lightweight UAV semantic segmentation with dynamic convolution, attention gates, and deep supervision (Applied Sciences submission)

Unofficial PyTorch reimplementation of SPCONet — real-time semantic segmentation fusing strip-pooling spatial features with dynamic-convolution context refinement over a ResNet-18 backbone (Intelligent Systems with Applications 2025).