MambaOut: Do We Really Need Mamba for Vision?

Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs (CVPR 2022)

[CVPR'24] UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition

ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks

InteractiveVideo: User-Centric Controllable Video Generation with Synergistic Multimodal Instructions

[CVPR'24] Multimodal Pathway: Improve Transformers with Irrelevant Data from Other Modalities

GroupMixAttention and GroupMixFormer

Unsupervised deep learning framework with online(MLP: prediction-based, 1 D Conv and VAE: reconstruction-based, Wavenet: prediction-based) settings for anaomaly detection in time series data

[NeurIPS'22] This is an official implementation for "Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning".

Diverse Branch Block: Building a Convolution as an Inception-like Unit

Keras (TensorFlow v2) reimplementation of Re-parameterized Large Kernel Network (RepLKNet)

RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality (CVPR 2022)

Is the attention layer even necessary? (https://arxiv.org/abs/2105.02723)

TensorRT implementation of "RepVGG: Making VGG-style ConvNets Great Again"

ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting (ICCV 2021)