Methods › General › Attention Mechanisms › Self-Calibrated Convolutions

Self-Calibrated Convolutions

2 papers tagged archive 2025-07-28

Introduced by Jiang-Jiang Liu et al. in Improving Convolutional Networks With Self-Calibrated Convolutions

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Liu et al. presented self-calibrated convolution as a means to enlarge the receptive field at each spatial location.

Self-calibrated convolution is used together with a standard convolution. It first divides the input feature X into X₁ and X₂ in the channel domain. The self-calibrated convolution first uses average pooling to reduce the input size and enlarge the receptive field: T₁ = AvgPoolᵣ(X₁) where r is the filter size and stride. Then a convolution is used to model the channel relationship and a bilinear interpolation operator Up is used to upsample the feature map:

X′₁ = Up(Conv₂(T₁))

Next, element-wise multiplication finishes the self-calibrated process:

Y′₁ = Conv₃(X₁) σ(X₁ + X′₁)

Finally, the output feature map of is formed: Y₁ = Conv₄(Y′₁) Y₂ = Conv₁(X₂) Y = [Y₁; Y₂] Such self-calibrated convolution can enlarge the receptive field of a network and improve its adaptability. It achieves excellent results in image classification and certain downstream tasks such as instance segmentation, object detection and keypoint detection.

PaperSource

Papers archive 2025-07-28

2 shown of 2, 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

9 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
Brain Tumor Segmentation1
Instance Segmentation1
Keypoint Detection1
Object Detection1
Representation Learning1
Segmentation1
Semantic Segmentation1
Tumor Segmentation1
object-detection1

Usage over time archive 2025-07-28

Papers per year tagged with Self-Calibrated Convolutions: 2020 to 2024, peak 1 1 0 2020: 1 paper 2020 2021: 0 papers 2021 2022: 0 papers 2022 2023: 0 papers 2023 2024: 1 paper 2024
Papers per year the archive tags with this method, by the paper's archive date (2 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

Attention Mechanisms

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