TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Methods/Selective Kernel Convolution

Selective Kernel Convolution

Computer VisionIntroduced 200029 papers
Source Paper

Description

A Selective Kernel Convolution is a convolution that enables neurons to adaptively adjust their RF sizes among multiple kernels with different kernel sizes. Specifically, the SK convolution has three operators – Split, Fuse and Select. Multiple branches with different kernel sizes are fused using softmax attention that is guided by the information in these branches. Different attentions on these branches yield different sizes of the effective receptive fields of neurons in the fusion layer

Papers Using This Method

OBIFormer: A Fast Attentive Denoising Framework for Oracle Bone Inscriptions2025-04-18SLAM in the Dark: Self-Supervised Learning of Pose, Depth and Loop-Closure from Thermal Images2025-02-26MoCoLSK: Modality Conditioned High-Resolution Downscaling for Land Surface Temperature2024-09-30Attention-Guided Multi-scale Interaction Network for Face Super-Resolution2024-09-01Pick-or-Mix: Dynamic Channel Sampling for ConvNets2024-06-16LSKSANet: A Novel Architecture for Remote Sensing Image Semantic Segmentation Leveraging Large Selective Kernel and Sparse Attention Mechanism2024-06-03MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space2024-05-25A Click-Through Rate Prediction Method Based on Cross-Importance of Multi-Order Features2024-05-14AC-MAMBASEG: An adaptive convolution and Mamba-based architecture for enhanced skin lesion segmentation2024-05-05LSKNet: A Foundation Lightweight Backbone for Remote Sensing2024-03-18CoFiNet: Unveiling Camouflaged Objects with Multi-Scale Finesse2024-02-03Innovative Horizons in Aerial Imagery: LSKNet Meets DiffusionDet for Advanced Object Detection2023-11-21Variational Relational Point Completion Network for Robust 3D Classification2023-04-18Large Selective Kernel Network for Remote Sensing Object Detection2023-03-16ESKNet-An enhanced adaptive selection kernel convolution for breast tumors segmentation2022-11-05TC-SKNet with GridMask for Low-complexity Classification of Acoustic scene2022-10-05CTooth: A Fully Annotated 3D Dataset and Benchmark for Tooth Volume Segmentation on Cone Beam Computed Tomography Images2022-06-17Frequency and Multi-Scale Selective Kernel Attention for Speaker Verification2022-04-03Selective Residual M-Net for Real Image Denoising2022-03-03TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation2022-02-27