Methods › General › Skip Connection Blocks › Selective Kernel

Selective Kernel

27 papers tagged archive 2025-07-28

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].

PaperSourceSee Code · osmr/imgclsmob

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.

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.

TaskPapers
Semantic Segmentation5
Object Detection4
Segmentation4
object-detection4
Image Classification3
Object3
Denoising2
Lesion Segmentation2
Object Detection In Aerial Images2
Point Cloud Completion2
Transfer Learning2
image-classification2
3D Classification1
Attribute1
AutoML1
Autonomous Driving1
Change Detection1
Classification1
Click-Through Rate Prediction1
Data Augmentation1

Usage over time archive 2025-07-28

Papers per year tagged with Selective Kernel: 2019 to 2025, peak 9 9 0 2019: 1 paper 2019 2020: 2 papers 2020 2021: 2 papers 2021 2022: 8 papers 2022 2023: 3 papers 2023 2024: 9 papers 2024 2025: 2 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (27 dated). Bars are counts, not a trend claim.

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

Skip Connection BlocksImage Model Blocks

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