Methods › Computer Vision › Image Data Augmentation › GridMask

GridMask

3 papers tagged archive 2025-07-28

Introduced by Pengguang Chen et al. in GridMask Data Augmentation

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

GridMask is a data augmentation method that randomly removes some pixels of an input image. Unlike other methods, the region that the algorithm removes is neither a continuous region nor random pixels in dropout. Instead, the algorithm removes a region with disconnected pixel sets, as shown in the Figure.

We express the setting as

𝐱̃=𝐱 ×M

where 𝐱 ∈R^(H ×W ×C) represents the input image, M ∈ {0,1}^(H ×W) is the binary mask that stores pixels to be removed, and 𝐱̃ ∈R^(H ×W ×C) is the result produced by the algorithm. For the binary mask M, if M_(i, j)=1 we keep pixel (i, j) in the input image; otherwise we remove it. GridMask is applied after the image normalization operation.

The shape of M looks like a grid, as shown in the Figure . Four numbers (r, d, δₓ, δ_y) are used to represent a unique M. Every mask is formed by tiling the units. r is the ratio of the shorter gray edge in a unit. d is the length of one unit. δₓ and δ_y are the distances between the first intact unit and boundary of the image.

PaperSource

Papers archive 2025-07-28

3 shown of 3, 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

10 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
Data Augmentation3
Semantic Segmentation2
AutoML1
Instance Segmentation1
Object Detection1
Reinforcement Learning1
Reinforcement Learning (RL)1
Segmentation1
object-detection1
reinforcement-learning1

Usage over time archive 2025-07-28

Papers per year tagged with GridMask: 2020 to 2022, peak 1 1 0 2020: 1 paper 2020 2021: 1 paper 2021 2022: 1 paper 2022
Papers per year the archive tags with this method, by the paper's archive date (3 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

Image Data Augmentation

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