Methods › General › Skip Connection Blocks › Selective Kernel
Selective Kernel
Introduced by Xiang Li et al. in Selective Kernel Networks
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
A Selective Kernel unit is a bottleneck block consisting of a sequence of 1×1 convolution, SK convolution and 1×1 convolution. It was proposed as part of the SKNet CNN architecture. In general, all the large kernel convolutions in the original bottleneck blocks in ResNeXt are replaced by the proposed SK convolutions, enabling the network to choose appropriate receptive field sizes in an adaptive manner.
In SK units, there are three important hyper-parameters which determine the final settings of SK convolutions: the number of paths M that determines the number of choices of different kernels to be aggregated, the group number G that controls the cardinality of each path, and the reduction ratio r that controls the number of parameters in the fuse operator. One typical setting of SK convolutions is SK[M, G, r] to be SK[2, 32, 16].
Papers archive 2025-07-28
27 shown of 27, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
OBIFormer: A Fast Attentive Denoising Framework for Oracle Bone Inscriptions 18 Apr 2025 · 1 repository · arXiv:2504.13524
-
SLAM in the Dark: Self-Supervised Learning of Pose, Depth and Loop-Closure from Thermal Images 26 Feb 2025 · 0 repositories · arXiv:2502.18932
-
MoCoLSK: Modality Conditioned High-Resolution Downscaling for Land Surface Temperature 30 Sep 2024 · 1 repository · arXiv:2409.19835
-
Attention-Guided Multi-scale Interaction Network for Face Super-Resolution 1 Sep 2024 · 0 repositories · arXiv:2409.00591
-
Pick-or-Mix: Dynamic Channel Sampling for ConvNets 16 Jun 2024 · 1 repository · arXiv:2406.10935
-
LSKSANet: A Novel Architecture for Remote Sensing Image Semantic Segmentation Leveraging Large Selective Kernel and Sparse Attention Mechanism 3 Jun 2024 · 0 repositories · arXiv:2406.01228
-
MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space 25 May 2024 · 0 repositories · arXiv:2405.16105
-
A Click-Through Rate Prediction Method Based on Cross-Importance of Multi-Order Features 14 May 2024 · 0 repositories · arXiv:2405.08852
-
AC-MAMBASEG: An adaptive convolution and Mamba-based architecture for enhanced skin lesion segmentation 5 May 2024 · 1 repository · arXiv:2405.03011
-
LSKNet: A Foundation Lightweight Backbone for Remote Sensing 18 Mar 2024 · 2 repositories · arXiv:2403.11735
-
CoFiNet: Unveiling Camouflaged Objects with Multi-Scale Finesse 3 Feb 2024 · 0 repositories · arXiv:2402.02217
-
Innovative Horizons in Aerial Imagery: LSKNet Meets DiffusionDet for Advanced Object Detection 21 Nov 2023 · 1 repository · arXiv:2311.12956
-
Variational Relational Point Completion Network for Robust 3D Classification 18 Apr 2023 · 0 repositories · arXiv:2304.09131
-
Large Selective Kernel Network for Remote Sensing Object Detection 16 Mar 2023 · 1 repository · arXiv:2303.09030
-
ESKNet-An enhanced adaptive selection kernel convolution for breast tumors segmentation 5 Nov 2022 · 1 repository · arXiv:2211.02915
-
TC-SKNet with GridMask for Low-complexity Classification of Acoustic scene 5 Oct 2022 · 0 repositories · arXiv:2210.02287
-
CTooth: A Fully Annotated 3D Dataset and Benchmark for Tooth Volume Segmentation on Cone Beam Computed Tomography Images 17 Jun 2022 · 1 repository · arXiv:2206.08778
-
Frequency and Multi-Scale Selective Kernel Attention for Speaker Verification 3 Apr 2022 · 1 repository · arXiv:2204.01005
-
Selective Residual M-Net for Real Image Denoising 3 Mar 2022 · 1 repository · arXiv:2203.01645
-
TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation 27 Feb 2022 · 2 repositories · arXiv:2202.13393
-
Faster hyperspectral image classification based on selective kernel mechanism using deep convolutional networks 14 Feb 2022 · 1 repository · arXiv:2202.06458
-
Attribute-Based Progressive Fusion Network for RGBT Tracking 26 Jan 2022 · 2 repositories
-
DRPN: Making CNN Dynamically Handle Scale Variation 21 Dec 2021 · 0 repositories · arXiv:2112.10963
-
Variational Relational Point Completion Network 20 Apr 2021 · 1 repository · arXiv:2104.10154
-
WaveGrad: Estimating Gradients for Waveform Generation 2 Sep 2020 · 7 repositories · arXiv:2009.00713Syntology ran 1 of 3 samples · 2 unverified · 1 pointer-only (licence)
-
Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network 17 Jan 2020 · 1 repository · arXiv:2001.06268Syntology ran 1 of 11 samples · 10 unverified
-
Selective Kernel Networks 15 Mar 2019 · 20 repositories · arXiv:1903.06586Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 51 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections