aug_cutout — 2D augmentation op

Data kinds: imageimage

Call: fullseye.apply(img, "aug_cutout", a=0.5, b=0.5) (the 2-D model is one image plus two scalar knobs a,b∈[0,1])

aug_cutout: input → output

*The figure is the actual output on a synthetic 128×128 input. Left: input, right: output. Point clouds are drawn as a top-down scatter (brightness = z), 1-D series as a line plot, volumes as the maximum-intensity projection along z, videos as the middle frame, complex images as magnitude; return values that are not pictures are shown as the values themselves.*

Sweeping knob a (0.1 / 0.5 / 0.9, the other knob at its default):

aug_cutout: knob a sweep (docs site)

Sweeping knob b (0.1 / 0.5 / 0.9, the other knob at its default):

aug_cutout: knob b sweep (docs site)

On other images (synthetic scene / photo / coins. Top row: inputs, bottom row: their outputs. Knobs at default):

aug_cutout: other inputs (docs site)

*The 4th column is a colour (H,W,3) input. This op handles colour without crossing channels (it does not convolve the colour channel as a third spatial axis).*

Usage

Cutout / random-erasing occlusion (DeVries & Taylor 2017; Zhong et al. 2020): a square patch of side `max(1, a*min(H,W)) is erased from the image, forcing a pipeline to survive partial occlusion instead of relying on one salient blob. b` selects the (deterministic, seeded-from-b) patch position AND the fill value: b <= 0.5 -> black (0.0), b > 0.5 -> mid-gray (0.5). The patch is always fully inside the frame.

Blank frame (measured): feeding an image of uniform brightness gives an empty result — every pixel is background (0) — regardless of the brightness. Pure white and pure black behave alike; brightness by itself detects nothing.

Detailed usage guide

gallery2d_color_artistic family guide

References (sample data, literature)

• Sample-data catalog (download URLs / licences) — 2-D uses skimage.data (BSD/public domain) plus synthetic images; 3-D lists download URLs for real data sources (Stanford, PDS, …).

• Operator provenance and references — the sources of the research/methods this op family came from.

• The canonical algorithm (author, year) and its uses are named in the family usage guide above.

Try it in Studio

The program below has been verified to run (same input as the figure). In Studio's help this block becomes buttons that load and run it on the spot.

aug_cutout 0.50 0.50

▸ Load this pipeline  ·  Load & run

Runnable examples (verified samples that actually call this op)

gallery2d_color_artisticpy -3.11 examples/gallery2d_color_artistic.py

Ops the type connects to (they accept image as input)

identity · gaussian · mean_box · bilateral · unsharp · median · min_filter · max_filter

Same category (augmentation)

aug_shot_noise · aug_read_noise · aug_fixed_pattern · aug_motion_blur · aug_vignette · aug_chromatic · aug_rolling_shutter · aug_jpeg_blocks


*Provenance: ops.py — 2D operator registry. This per-op note is generated by tools/opdocs.py md (do not hand-edit).*

© 2026 Kazufumi Furuse — Fullseye operator documentation. Licensed under Apache-2.0.