ShqWW / dwconv2dLinks
This is an efficient cuda implementation of 2D depthwise convolution for large kernel, it can be used in Pytorch deep learning framework.
☆10Updated last year
Alternatives and similar repositories for dwconv2d
Users that are interested in dwconv2d are comparing it to the libraries listed below
Sorting:
- [ICML 2024] Official PyTorch implementation of "SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-paramete…☆105Updated 9 months ago
- This is the official pytorch implementation for the paper: Towards Accurate Post-training Quantization for Diffusion Models.(CVPR24 Poste…☆36Updated last year
- [CVPR'23] SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer☆69Updated last year
- [BMVC 2024] PlainMamba: Improving Non-hierarchical Mamba in Visual Recognition☆77Updated 2 months ago
- ☆20Updated last year
- [CVPR 2024] PTQ4SAM: Post-Training Quantization for Segment Anything☆74Updated 11 months ago
- [ICLR 2025] Official PyTorch implementation of "DECO: Query-Based End-to-End Object Detection with ConvNets"☆51Updated 4 months ago
- Official Implementation of Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object Detection☆49Updated last year
- ALGM applied to Segmenter☆24Updated last year
- Official implementation of "SViT: Revisiting Token Pruning for Object Detection and Instance Segmentation"☆32Updated last year
- The official implementation of the NeurIPS 2022 paper Q-ViT.☆89Updated 2 years ago
- This repository is the official implementation of "Partial Channel Network: Compute Fewer, Perform Better", which includes training, eval…☆14Updated 3 months ago
- [NeurIPS 2023 Spotlight] This project is the official implementation of our accepted NeurIPS 2023 (spotlight) paper QuantSR: Accurate Low…☆47Updated last year
- [ICCV 23]An approach to enhance the efficiency of Vision Transformer (ViT) by concurrently employing token pruning and token merging tech…☆96Updated last year
- Official Pytorch implementation of Dynamic-Token-Pruning (ICCV2023)☆21Updated last year
- [CVPR 2023] Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention During Vision Transformer Inference☆30Updated last year
- Implementation of Hire-MLP: Vision MLP via Hierarchical Rearrangement and An Image Patch is a Wave: Phase-Aware Vision MLP.☆37Updated 2 years ago
- ☆26Updated 2 months ago
- [ICLR 2024 poster] Efficient Modulation for Vision Networks☆53Updated 11 months ago
- [AAAI 2025] Linear-complexity Visual Sequence Learning with Gated Linear Attention☆111Updated 11 months ago
- [CVPR'24] Official implementation of paper "FreeKD: Knowledge Distillation via Semantic Frequency Prompt".☆44Updated last year
- [ECCV 2024 Workshop Best Paper Award] Famba-V: Fast Vision Mamba with Cross-Layer Token Fusion☆33Updated 8 months ago
- Official repository of InLine attention (NeurIPS 2024)☆47Updated 5 months ago
- [CVPR 2025] "DiC: Rethinking Conv3x3 Designs in Diffusion Models", a performant & speedy Conv3x3 diffusion model.☆20Updated 3 months ago
- Dynamic Multi-scale Filters for Semantic Segmentation (DMNet ICCV'2019)☆27Updated 3 years ago
- ☆82Updated 9 months ago
- FFNet: MetaMixer-based Efficient Convolutional Mixer Design☆27Updated 2 months ago
- [CVPR 2025] The official implementation of "CacheQuant: Comprehensively Accelerated Diffusion Models"☆22Updated 2 weeks ago
- [NeurIPS2024 Spotlight] The official implementation of MambaTree: Tree Topology is All You Need in State Space Model☆92Updated 11 months ago
- PyTorch code and checkpoints release for VanillaKD: https://arxiv.org/abs/2305.15781☆75Updated last year