ysj9909 / SHViT
[CVPR 2024] SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design
☆68Updated 5 months ago
Related projects ⓘ
Alternatives and complementary repositories for SHViT
- The official code of "Rethinking Local Perception in Lightweight Vision Transformer"☆84Updated last year
- [ICLR 2024 poster] Efficient Modulation for Vision Networks☆48Updated 4 months ago
- GroupMixAttention and GroupMixFormer☆113Updated 11 months ago
- Code Implementation of EfficientVMamba☆183Updated 7 months ago
- The official project website of "KernelWarehouse: Rethinking the Design of Dynamic Convolution" (KW for short, accepted to ICML 2024)☆95Updated 5 months ago
- RepNeXt: A Fast Multi-Scale CNN using Structural Reparameterization☆33Updated last month
- ☆128Updated 4 months ago
- CVPR 2024 Highlight: Frequency-Adaptive Dilated Convolution for Semantic Segmentation☆95Updated last week
- Mamba in Vision: A Comprehensive Survey of Techniques and Applications☆70Updated last month
- ☆80Updated last year
- This is an official implementation for "Scale-Aware Modulation Meet Transformer".☆193Updated last year
- This is the repository for TNNLS paper UniHead☆12Updated last month
- ☆70Updated last year
- Code for paper LocalMamba: Visual State Space Model with Windowed Selective Scan☆204Updated 6 months ago
- SCSA: Exploring the Synergistic Effects Between Spatial and Channel Attention.☆41Updated 4 months ago
- Official implementation of the CVPR 2024 paper ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense…☆231Updated last month
- [NeurIPS2024] Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model☆47Updated last month
- ☆47Updated 8 months ago
- CrossKD: Cross-Head Knowledge Distillation for Dense Object Detection☆143Updated last year
- ☆83Updated this week
- (CVPR2023/TPAMI2024) Integrally Pre-Trained Transformer Pyramid Networks -- A Hierarchical Vision Transformer for Masked Image Modeling☆175Updated 3 months ago
- ☆121Updated last year
- ☆116Updated 2 months ago
- [ICML 2024] Official PyTorch implementation of "SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-paramete…☆79Updated 2 months ago
- Official repository of Slide-Transformer (CVPR2023)☆162Updated 2 months ago
- [CVPR 2024] Rewrite the Stars☆286Updated 6 months ago
- ☆149Updated last year
- TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognition☆161Updated 11 months ago
- Vision Mamba: A Comprehensive Survey and Taxonomy☆81Updated 2 months ago
- [ICCV 2023] Official PyTorch implementation of "Rethinking Mobile Block for Efficient Attention-based Models"☆229Updated last year